DETAILED ACTION
This action is responsive to the Amendments and Remarks received 03/31/2026 in which no claims are cancelled, claims 1–6, 8–10, 15–17, 19, and 20 are amended, and no claims are added as new claims.
Response to Arguments
In view of the amendment to claim 10, the objection is withdrawn. Remarks, 12.
Applicant’s amendments do not change the interpretation under 35 U.S.C. 112(f). Therefore, claims 8–14 are interpreted to invoke 35 U.S.C. 112(f). Remarks, 12.
The rejection of claims 8–14 under 35 U.S.C. 112(a) as single means claims is withdrawn. Remarks, 12.
On page 15 of the Remarks, Applicant contends the teachings of Rajabi are “fundamentally different from” quoted claim language, but fails to specify why or in what way. Simply contending, without evidence or reasoning, that a prior art teaching is different from the claimed features, without explaining how they differ is unpersuasive of error. A “mere recitation of the claim elements and a naked assertion that the corresponding elements [are] not found in the prior art” is not persuasive of error. See In re Lovin, 652 F.3d 1349, 1357 (Fed. Cir. 2011).
On page 16 of the Remarks, Applicant contends the teachings of McKiel are not sufficient to teach or suggest the claimed subject matter. Examiner disagrees. Applicant argues that while McKiel teaches adding surface text to a 3D object, such a teaching does not teach or suggest modifying editable text in a raster image such that it conforms to the depth perspective of the 2D image. Examiner disagrees and finds Applicant treats the references individually rather than what their combination would teach or suggest to one of ordinary skill in the art. The skilled artisan knows that text can be recognized in an image through OCR even when the text wraps around a 3D object, such as a cylinder. See Applicant’s Fig. 2 and compare it to the teachings of Choi. At the outset, it is important to note that in this art, skilled artisans can develop a workflow for image processing wherein discrete, modular steps are performed to generate a desired outcome. According to Choi, a user can take a raster photo of a bottle of wine and the image can be processed to recognize text on the label by creating a 2D projection of the text from the 3D-warped object within the raster image (see e.g. Choi, Fig. 1). As shown in Choi’s Fig. 3, the distortion of the label, due to it being wrapped around the cylindrical bottle, can be removed by recognizing the 3D parameters that define the wrapping of the label around the bottle. Dewarping functions (geometric transforms) are well-represented in the art. The rejection then explains that Choi’s process of extracting a texture from a 3D object in a raster image is the inverse of applying a 2D texture on a 3D object such that the skilled artisan would recognize the 2D recognized text extracted from the 3D object as taught in Choi could then be used as a texture that could be applied to a 3D object and converted back into a raster image of the 3D object having a texture (label) applied thereon. These wrapping functions (UV or texture mapping or warping functions) are well-represented in the art. Once the label is converted into a 2D orthogonal image with distortion removed, conventional OCR technology can convert the text image into a text object, which can be copied, altered, deleted, searched, etc. as described in Rajabi. As the rejection explains, Rajabi evidences that the skilled artisan was aware that OCR tools can identify and store text within a 2D image as editable characters. Finally, McKiel teaches the skilled artisan had in his possession the ability to freely type text using a text object placed onto the surface of a 3D object as a texture without changing the underlying 3D model so that text is editable on the 3D manifold as a texture object. Therefore, the combination of the teachings of Choi, Rajabi, and McKiel represents an obvious combination of image processing tasks collectively representing a workflow, which is a common approach to complex image processing tasks in this technological field. Because Applicant’s attack on the references in isolation does not address what the combination would teach or suggest to one of ordinary skill, it is unpersuasive of error. Accordingly, the rejections under 35 U.S.C. 103 are sustained.
On pages 17–18 of the Remarks, regarding claim 8, Applicant contends prior art not relied upon for teaching a feature fail to teach that feature. Examiner interprets these arguments to not be particularly relevant to the rejections of record and are, therefore, unpersuasive of error.
On pages 18–21 of the Remarks, regarding claim 15, Applicant contends prior art not relied upon for teaching a feature fail to teach that feature. Examiner interprets these arguments to not be particularly relevant to the rejections of record and are, therefore, unpersuasive of error.
Other claims are not argued separately. Remarks, 20.
Claim Objections
Claim 17 is objected to for the following informality: The claim ends with the phrasing, “a raster digital raster image.” Two occurrences of the term, “raster,” seems duplicative. Appropriate correction is required.
35 USC § 112(f)
35 U.S.C. 112(f) reads as follows:
An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
Claims 8–14 disclose limitations that invoke 35 U.S.C. 112(f) under the analysis described in MPEP 2181.
According to MPEP 2181, 35 U.S.C. 112(f) is invoked by claim limitations that meet the following conditions: (1) the claim limitation uses the term “means” or “step” or a term used as a substitute for “means” that is a generic placeholder (also called a nonce term or a non-structural term having no specific structural meaning) for performing the claimed function; (2) the non-structural term is modified by functional language, typically, but not always linked by the transition word “for” or another linking word or phrase, such as “configured to” or “so that”; and (3) the non-structural term is not modified by sufficient structure, material, or acts for achieving the specified function. “Where a claim limitation meets the 3-prong analysis and is being treated under 35 U.S.C. 112, sixth paragraph, the examiner will include a statement in the Office action that the claim limitation is being treated under 35 U.S.C. 112, sixth paragraph.” MPEP 2181(I)(C).
In claims 8–14, Applicant uses the phrase “processor configured to” for several limitations. In each case, Examiner interprets such language as a non-structural term followed by a linking word or phrase, which links the non-structural term to recited functions. In each case, the non-structural term is modified by functional language and is not modified by sufficient structure. Therefore, the claims invoke 35 U.S.C. 112(f). MPEP 2181(I).
Examiner finds that the units operable to perform the recited functions of claims 8–14 could be broadly construed as software modules or subroutines, or a computer or similar processing circuit or system of processors. Regarding the interpretation that the units might be a processor or group of processors, the Examiner considered whether the functions recited in claims 8–14 are functions typically found in a commercially available off-the-shelf processor. See In re Katz Interactive Call Processing Patent Litigation, 639 F.3d 1303, 1316 (Fed. Cir. 2011) (functions such as "processing," "receiving," and "storing" that can be achieved by any general purpose computer without special programming do not require disclosure of more structure than the general purpose processor that performs those functions). Because the recited functions are the substance and focus of the invention claimed, the Examiner finds these functions are not typically available in an off-the-shelf processor. Therefore, the Examiner finds the functional recitations do not connote to the skilled artisan sufficient structure of the processors (or similar) claimed. Accordingly, the phrase “process configured to” is interpreted as invoking the application of 35 U.S.C. § 112(f).
Claim Rejections - 35 USC § 112(a)
The following is a quotation of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
Claims 1–20 are rejected under 35 U.S.C. 112(a) as failing to comply with the enablement requirement. The claims contain subject matter which was not described in the specification in such a way as to enable one skilled in the art to which it pertains, or with which it is most nearly connected, to make and/or use the invention. Specifically, the claims recite result to be achieved rather than any particular structure or step to achieve the claimed result. Aristocrat, 521 F.3d, 1334 (criticizing claim language that claims an outcome rather than the means for achieving the outcome). At the least, such an approach to claiming an invention is dubious under an enablement analysis. Sitrick v. Dreamworks, LLC, 516 F.3d 993, 999, 85 USPQ2d 1826, ____ (Fed. Cir. 2008) (“The scope of the claims must be less than or equal to the scope of the enablement to ensure that the public knowledge is enriched by the patent specification to a degree at least commensurate with the scope of the claims.”) (quotation omitted). Whether undue experimentation is needed is not a single, simple factual determination, but rather is a conclusion reached by weighing many factual considerations. In re Wands, 858 F.2d at 737. The Wands factors include: (1) the quantity of experimentation necessary, (2) the amount of direction or guidance presented, (3) the presence or absence of working examples, (4) the nature of the invention, (5) the state of the prior art, (6) the relative skill of those in the art, (7) the predictability or unpredictability of the art, and (8) the breadth of the claims. In reviewing for lack of enablement, the Wands court elected to consider “all of the factors.” Id. at 740. However, it is not necessary to review all the Wands factors to find a disclosure enabling. Rather, the Wands factors “are illustrative, not mandatory” and what is relevant to an enablement determination depends upon the facts of the particular case. See Amgen, Inc. v. Chugai Pharm. Co., 927 F.2d 1200, 1213 (Fed. Cir. 1991). See also Enzo Biochem, Inc. v. Calgene, Inc., 188 F.3d 1362, 1373 (Fed. Cir. 1999) and Warner-Lambert Company v. Teva Pharmaceuticals USA, Inc., 418 F.3d 1326, 1337 (Fed. Cir. 2005). Where the specification is deficient in describing every means for achieving the claimed results, the claims are not enabled. See also ChargePoint, Inc. v. SemaConnect, Inc. (2019). According to the court, the claim merely demanded a result without any limitation on how to produce that result, running afoul of precedents like Interval Licensing LLC v. AOL, Inc., 896 F.3d 1335 (Fed. Cir. 2018) where the court wrote that claims that “simply demand the production of a desired result . . . without any limitation on how to produce that result” are directed to an abstract idea. Viewed as duplicative, Examiner elects not to levy an abstract idea rejection on the claims at this time.
Claim Rejections - 35 USC § 112(b)
The following is a quotation of 35 U.S.C. 112:
(B) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
Claim XXX rejected under 35 U.S.C. 112(b) as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor, or for pre-AIA the applicant regards as the invention.
Claims 8–14 are rejected under 35 U.S.C. 112(b) as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor, or for pre-AIA the applicant regards as the invention. Specifically, claims 8–14 represent single means claims. A single element cannot rely on 35 U.S.C. 112(f) to incorporate the structure from the specification because 35 U.S.C. 112(f) only applies to claims for a combination (more than one element). Without the benefit of the 112(f) construction, the broadest reasonable interpretation of this claim extends to all ways of achieving the claimed results, including those known and unknown to the inventor, and amounts to pure functional claiming without boundaries in violation of 35 U.S.C. 112(b).
Claims 8–14 contain limitations that invoke 35 U.S.C. 112(f). However, the written description fails to disclose the corresponding structure, material, or acts for the claimed functions.
Applicant may:
(a) Amend the claim so that the claim limitation will no longer be interpreted as a limitation under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph;
(b) Amend the written description of the specification such that it expressly recites what structure, material, or acts perform the entire claimed function, without introducing any new matter (35 U.S.C. 132(a)); or
(c) Amend the written description of the specification such that it clearly links the structure, material, or acts disclosed therein to the function recited in the claim, without introducing any new matter (35 U.S.C. 132(a)).
If applicant is of the opinion that the written description of the specification already implicitly or inherently discloses the corresponding structure, material, or acts and clearly links them to the function so that one of ordinary skill in the art would recognize what structure, material, or acts perform the claimed function, applicant should clarify the record by either:
(a) Amending the written description of the specification such that it expressly recites the corresponding structure, material, or acts for performing the claimed function and clearly links or associates the structure, material, or acts to the claimed function, without introducing any new matter (35 U.S.C. 132(a)); or
(b) Stating on the record what the corresponding structure, material, or acts, which are implicitly or inherently set forth in the written description of the specification, perform the claimed function. For more information, see 37 CFR 1.75(d) and MPEP §§ 608.01(o) and 2181.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102 of this title, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1 and 2 are rejected under 35 U.S.C. 103 as being unpatentable over Choi (US 2023/0343061 A1), Rajabi (US 2026/0045053 A1), and McKiel (US 2024/0109244 A1).
Regarding claim 1, the combination of Choi, Rajabi, and McKiel teaches or suggests a computer-implemented method comprising: detecting, from a digital raster image displayed by a client device, a text segment comprising non-editable text portrayed in accordance with a depth perspective of the digital raster image (Choi, Abstract, ¶ 0081, and e.g. Fig. 1: teaches performing a perspective transformation on a curved surface of a 3D object to flatten the surface for purposes of generating a 2D surface; See also Choi, Fig. 9A: demonstrating the text fields recognized as objects on the label; Compare Applicant’s Fig. 2; Choi, e.g. Fig. 3 and ¶ 0272: teach the image(s) are 2D digital raster images taken, for example, by a conventional camera; see also McKiel, infra, describing the surface text object projected onto an object manifold in the image being a raster or bitmap; Examiner further notes UV maps are a flattened region of texture from a 3D mesh and can be extracted or applied from/to the mesh structure using e.g. surface normals; Examiner finds editable text as a texture applied to the surface of a mesh object is well-represented in this art; see e.g. videos and forum threads cited under the Conclusion Section of this Office Action; In a workflow, a 2D raster image can be converted to a mesh and then the workflow can proceed from there utilizing conventional texture maps and conventional text editing of text objects; Indeed, original claim 3 explains the workflow includes converting the 2D raster image into a 3D mesh); generating, within the digital raster image and from the text segment portrayed in the digital raster image, an editable text object having editable text generated from the non-editable text of the text segment, the editable text object following the depth perspective of the digital raster image by visually conforming to a three-dimensional appearance of at least a portion of the digital raster image (Rajabi, ¶ 0064: teaches OCR tools can identify and store text within a 2D raster image as editable characters and providing new text within a 3D object); and modifying, in response to receiving one or more user interactions via the client device, the editable text of the editable text object in accordance with the depth perspective of the digital raster image such that the modified editable text object portrayed in the digital raster image visually conforms to the three-dimensional appearance of the at least the portion of the digital raster image (Choi, e.g. Fig. 9B: teaches text boxes in an image that the skilled artisan would understand could be a recognized text object with an editable property; McKiel, ¶ 0121: teaches, via an end-user, freely typed text using a text object placed onto the surface of a 3D object and freely changing surface graphics or textures without changing (accessing) the underlying model wherein the text object can be a digital raster image; It is noted McKiel’s teachings are not limited to 3D CAD objects and that McKiel’s teachings explicitly explain, “the shape of an object [can] originate from [any] source” such that raster images can be a source of 3D object information; Jubi, cited under the Conclusion Section of this Office Action alternatively teaches this feature).
One of ordinary skill in the art, before the effective filing date of the claimed invention, would have been motivated to combine the elements taught by Choi, with those of Rajabi, because both Choi and Rajabi recognize the benefits of utilizing OCR in a 3D or imaging environment to extract text from objects and because combining Choi’s OCR with Rajabi’s simple explanation that OCR allows for text editing represents a mere combination of prior art elements, according to known methods, to yield a predictable result. This rationale applies to all combinations of Choi and Rajabi used in this Office Action unless otherwise noted.
One of ordinary skill in the art, before the effective filing date of the claimed invention, would have been motivated to combine the elements taught by Choi and Rajabi, with those of McKiel, because all three references are drawn to text recognition and/or manipulation in a 3D or imaging environment and because the skilled artisan would find Rajabi’s OCR allowing for text editing could be implemented using McKiel’s text editing that assigns an editable text object within a 3D environment such that the combination represents a mere combination of prior art elements, according to known methods, to yield a predictable result. This rationale applies to all combinations of Choi, Rajabi, and McKiel used in this Office Action unless otherwise noted.
Regarding claim 2, the combination of Choi, Rajabi, and McKiel teaches or suggests the computer-implemented method of claim 1, wherein detecting the text segment portrayed in accordance with the depth perspective of the digital raster image comprises detecting, utilizing an object detection model, a text region within the digital raster image, the text region comprising the text segment portrayed in accordance with the depth perspective of the digital raster image and a bounding box around the text region (Examiner notes the depiction of a bounding box around a text object in an image demonstrates the detection of the text region; Choi, ¶ 0085: teaches a detection model for extracting information from an ROI of an image; Choi, Fig. 9A: illustrates the text regions are indicated using bounding boxes).
Claim 3 is rejected under 35 U.S.C. 103 as being unpatentable over Choi, Rajabi, McKiel, Nagano (US 2024/0104842 A1), and Varekamp (US 2020/0177868 A1).
Regarding claim 3, the combination of Choi, Rajabi, McKiel, Nagano, and Varekamp teaches or suggests the computer-implemented method of claim 1, further comprising: generating a three-dimensional mesh of the digital raster image based on a depth map of the digital raster image (Nagano, ¶¶ 0048 and 0062: teaches auxiliary 3D information, such as depth map data, can be used to aid in the creation of a 3D mesh from a 2D image) by extracting a set of sample points from the depth map based on depth variation of the depth map and generating a triangle mesh from the set of sample points (Varekamp, ¶¶ 0165 and 0167: teach conversion of a depth map to a mesh based on variation of the depth map to generate a triangle mesh); and generating a three-dimensional mesh structure by combining the three-dimensional mesh with the digital image (Nagano, ¶ 0049: teaches generating a 3D mesh from a single 2D image; Examiner notes this is a known feature in this art; see references cited under the Conclusion Section of this Office Action; also consider Meta’s SAM3D; Varekamp, ¶¶ 0015 and 0113: teaches mapping a 2D texture map onto the 3D mesh), wherein generating the editable text object that follows the depth perspective of the digital raster image comprises generating the editable text object from the three-dimensional mesh structure (McKiel, ¶ 0121: teaches freely typed text using a text object placed onto the surface of a 3D object and freely changing surface graphics or textures without changing the underlying model; Jubi, cited under the Conclusion Section of this Office Action alternatively teaches this feature).
One of ordinary skill in the art, before the effective filing date of the claimed invention, would have been motivated to combine the elements taught by Choi, Rajabi, and McKiel, with those of Nagano, because both Choi and Nagano are drawn to the same field of endeavor such that one wishing to practice 3D modeling of objects would be led to their relevant teachings and because Choi’s step of performing a 2D projection of a texture, like text, from a previous generation step like Nagano’s generation of a 3D mesh represents nothing more than a standard computer-graphics workflow or pipeline such that the combination represents a mere combination of prior art elements, according to known methods, to yield a predictable result. This rationale applies to all combinations of Choi, Rajabi, McKiel, and Nagano used in this Office Action unless otherwise noted.
One of ordinary skill in the art, before the effective filing date of the claimed invention, would have been motivated to combine the elements taught by Choi, Rajabi, McKiel, and Nagano, with those of Varekamp, because both Nagano and Varekamp are drawn to generating a 3D representation from a 2D input image and because the skilled artisan would look to Varekamp’s teaching of how to generate a triangle mesh utilizing depth map variance to achieve Nagano’s generation of a 3D mesh given both references are drawn to solving the problem of converting a 2D input image into a 3D mesh such that their combination represents a mere combination of prior art elements, according to known methods, to yield a predictable result. This rationale applies to all combinations of Choi, Rajabi, McKiel, Nagano, and Varekamp used in this Office Action unless otherwise noted.
Claims 4 and 6 are rejected under 35 U.S.C. 103 as being unpatentable over Choi, Rajabi, McKiel, and The CG Essentials, “How to Use the SHRINKWRAP Modifier in Blender for Beginners!,” January 31, 2022, YouTube, https://www.youtube.com/watch?v=YksPYPa05LM, accessed 02/26/2026 (herein “CG Essentials”).
Regarding claim 4, the combination of Choi, Rajabi, McKiel, and CG Essentials teaches or suggests the computer-implemented method of claim 1, wherein generating the editable text object that follows the depth perspective of the digital raster image comprises: generating, from the digital raster image, a two-dimensional representation of a text region that includes the text segment by projecting the text region onto a two-dimensional surface using a triangle mesh of a three-dimensional mesh structure (Choi, Abstract, ¶ 0081, and e.g. Fig. 1: teaches performing a perspective transformation on a curved surface of a 3D object to flatten the surface for purposes of generating a 2D surface representing a detected text region; Compare Applicant’s Fig. 2; Examiner notes UV maps are a flattened region of texture from a 3D mesh and can be extracted or applied from/to the mesh structure using e.g. surface normals; Examiner finds editable text as a texture applied to the surface of a mesh object is well-represented in this art; see e.g. videos and forum threads cited under the Conclusion Section of this Office Action; Examiner takes Official Notice that a triangular mesh is the most common type of mesh, as evidenced by Laddha, cited under the Conclusion Section of this Office Action); generating the editable text object from the two-dimensional representation of the text region (Choi, ¶¶ 0133, 0138, and 0175: teach that once the region of interest is flattened, OCR can be used for extracting information from the region (e.g. label); Compare Applicant’s Fig. 2; Rajabi, ¶ 0064: teaches OCR tools can identify and store text within a 2D image as editable characters and providing new text within a 3D object; Examiner notes the skilled artisan has in their possession OCR technology allowing for editable text and further notes that text as objects is a conventional computer graphics feature; McKiel, ¶ 0121: teaches the text box is a text object within the 3D environment); and projecting the editable text object onto an underlying three-dimensional structure of the digital image (McKiel, ¶ 0121: teaches freely typed text using a text object placed onto the surface of a 3D object and freely changing surface graphics or textures without changing the underlying model; Projecting a 2D image texture onto the surface of a 3D mesh, for example as a UV map, is well-represented in this art; Choi’s undistort transformation would merely have to be reversed to apply the label back onto the bottle after editing in accordance with the deformation/warp function originally used to flatten the label; Examiner finds Blender’s SHRINKWRAP/projection modifier accomplishes this feature; CG Essentials, Minute 4:57: demonstrates the shrinkwrap modifier using a projection function to create a surface “sticker”.).
One of ordinary skill in the art, before the effective filing date of the claimed invention, would have been motivated to combine the elements taught by Choi, Rajabi, and McKiel, with those of CG Essentials, because both Choi and CG Essentials are drawn to the same field of endeavor such that one wishing to practice projection from/to a 3D mesh from/to a 2D image plane would be led to their relevant teachings regarding projection/perspective transformation and because reversing Choi’s projection from a 3D object to a 2D plane in the manner described by CG Essentials wherein the 2D plane is projected back onto the 3D object is an obvious workflow for computer graphics designers such that the combination represents a mere combination of prior art elements, according to known methods, to yield a predictable result. This rationale applies to all combinations of Choi, Rajabi, McKiel, and CG Essentials used in this Office Action unless otherwise noted.
Regarding claim 6, the combination of Choi, Rajabi, McKiel, and CG Essentials teaches or suggests the computer-implemented method of claim 4, wherein projecting the editable text object onto the underlying three-dimensional structure of the digital raster image comprises aligning, utilizing non-linear transformation, the editable text object with the underlying three-dimensional structure (Examiner notes a non-linear transform function is like a warp or projection that utilizes curves rather than straight lines and further interprets the claim to mean that the editable text is in 3D curved (i.e. non-linear) space such that the text object must be wrapped, i.e. shrinkwrapped, around an object such as a cylinder; McKiel, ¶ 0121: teaches freely typed text using a text object placed onto the surface of a 3D object and freely changing surface graphics or textures without changing the underlying model; Jubi, cited under the Conclusion Section of this Office Action alternatively teaches this feature).
Claims 7 and 15–19 are rejected under 35 U.S.C. 103 as being unpatentable over Choi, Rajabi, McKiel, and Kirchmayer (US 2023/0334754 A1).
Regarding claim 7, the combination of Choi, Rajabi, McKiel, and Kirchmayer teaches or suggests the computer-implemented method of claim 1, further comprising: generating one or more content fills for the editable text object using an image completion model; and exposing the one or more content fills upon modifying the editable text object (Kirchmayer, ¶ 0117: teaches ANN or GAN or CNN used for image completion for filling in holes in a 3D reconstruction including completing incomplete textures; Examiner notes that when the text is edited, background content can be uncovered required in-painting such as that described in Kirchmayer).
One of ordinary skill in the art, before the effective filing date of the claimed invention, would have been motivated to combine the elements taught by Choi, Rajabi, and McKiel, with those of Kirchmayer, because both Choi and Kirchmayer are drawn to the same field of endeavor such that one wishing to practice 3D reconstruction from 2D images (Kirchmayer, e.g. ¶ 0072) would be led to their relevant teachings regarding projection/perspective transformation and because combining the 3D reconstruction with a hole-filling neural network is an obvious addition to a workflow for computer graphics designers such that the combination represents a mere combination of prior art elements, according to known methods, to yield a predictable result. This rationale applies to all combinations of Choi, Rajabi, McKiel, and Kirchmayer used in this Office Action unless otherwise noted.
Regarding claim 15, the combination of Choi, Rajabi, McKiel, and Kirchmayer teaches or suggests a non-transitory computer-readable medium storing executable instructions which, when executed by a processing device, cause the processing device to perform operations comprising: detecting, from a digital raster image displayed by a client device, a text segment comprising non-editable text portrayed in accordance with a depth perspective of the digital raster image (Choi, Abstract, ¶ 0081, and e.g. Fig. 1: teaches performing a perspective transformation on a curved surface of a 3D object to flatten the surface for purposes of generating a 2D surface; See also Choi, Fig. 9A: demonstrating the text fields recognized as objects on the label; Compare Applicant’s Fig. 2; Examiner notes UV maps are a flattened region of texture from a 3D mesh and can be extracted or applied from/to the mesh structure using e.g. surface normals; Examiner finds editable text as a texture applied to the surface of a mesh object is well-represented in this art; see e.g. videos and forum threads cited under the Conclusion Section of this Office Action); generating, within the digital raster image and from the text segment portrayed in the digital raster image, an editable text object having editable text generated from the non-editable text of the text segment, the editable text object following the depth perspective of the digital raster image by visually conforming to a three-dimensional appearance of at least a portion of the digital raster image (Rajabi, ¶ 0064: teaches OCR tools can identify and store text within a 2D image as editable characters and providing new text within a 3D object); generating, using an image completion model, one or more content fills for the editable text object (Kirchmayer, ¶ 0117: teaches ANN or GAN or CNN used for image completion for filling in holes in a 3D reconstruction including completing incomplete textures; Examiner notes that when the text is edited, background content can be uncovered required in-painting such as that described in Kirchmayer); modifying, in response to receiving one or more user interactions via the client device, the editable text of the editable text object in accordance with the depth perspective of the digital raster image (McKiel, ¶ 0121: teaches freely typed text using a text object placed onto the surface of a 3D object and freely changing surface graphics or textures without changing the underlying model; Jubi, cited under the Conclusion Section of this Office Action alternatively teaches this feature) such that the modified editable text object portrayed in the digital raster image visually conforms to the three-dimensional appearance of the at least the portion of the digital raster image (Choi, e.g. Fig. 9B: teaches text boxes in an image that the skilled artisan would understand could be a recognized text object with an editable property; McKiel, ¶ 0121: teaches, via an end-user, freely typed text using a text object placed onto the surface of a 3D object and freely changing surface graphics or textures without changing (accessing) the underlying model wherein the text object can be a digital raster image; It is noted McKiel’s teachings are not limited to 3D CAD objects and that McKiel’s teachings explicitly explain, “the shape of an object [can] originate from [any] source” such that the 3D information can originate from 2D raster image, for example; Jubi, cited under the Conclusion Section of this Office Action alternatively teaches this feature), wherein modifying the editable text object exposes the one or more content fills (Kirchmayer, ¶ 0117: teaches ANN or GAN or CNN used for image completion for filling in holes in a 3D reconstruction including completing incomplete textures; Examiner notes that when the text is edited, background content can be uncovered required in-painting such as that described in Kirchmayer).
Regarding claim 16, the combination of Choi, Rajabi, McKiel, and Kirchmayer teaches or suggests the non-transitory computer-readable medium of claim 15, wherein detecting the text segment portrayed in accordance with the depth perspective of the digital raster image comprises detecting the text segment portrayed on an object of the digital raster image, the object following the depth perspective of the digital raster image (Examiner notes the depiction of a bounding box around a text object in an image demonstrates the detection of the text region; Choi, ¶ 0085: teaches a detection model for extracting information from an ROI of an image; Choi, Fig. 9A: teaches text object detection regions and bounding boxes that distinguish between one or more regions).
Regarding claim 17, the combination of Choi, Rajabi, McKiel, and Kirchmayer teaches or suggests the non-transitory computer-readable medium of claim 15, wherein generating the editable text object within the digital raster image comprises generating the editable text object within a raster digital raster image (Choi, Fig. 1: teaches the image used for the text object detection is a cell phone camera, which is a raster digital image; Rajabi, ¶ 0064: teaches OCR tools can identify and store text within a 2D image as editable characters and providing new text within a 3D object; Examiner notes the skilled artisan has in their possession OCR technology allowing for editable text and further notes that text as objects is a conventional computer graphics feature; McKiel, ¶ 0121: teaches the text box is a text object within the 3D environment).
Regarding claim 18, the combination of Choi, Rajabi, McKiel, and Kirchmayer teaches or suggests the non-transitory computer-readable medium of claim 15, further comprising determining that the text segment is targeted for modification by determining that control point coordinates of input received via the client device intersect with a bounding box of a text region corresponding to the text segment (Examiner notes the depiction of a bounding box around a text object in an image demonstrates the detection of the text region; Choi, ¶ 0085: teaches a detection model for extracting information from an ROI of an image; Choi, Fig. 9A: illustrates the text regions are indicated using bounding boxes; Examiner further notes that the claimed intersection is simply selecting the text box as an active window for purposes of modification), wherein generating the editable text object from the text segment comprises generating the editable text object based on determining that the text segment is targeted for modification (Rajabi, ¶ 0064: teaches OCR tools can identify and store text within a 2D image as editable characters and providing new text within a 3D object; Examiner notes the skilled artisan has in their possession OCR technology allowing for editable text and further notes that text as objects is a conventional computer graphics feature; McKiel, ¶ 0121: teaches the text box is a text object within the 3D environment).
Regarding claim 19, the combination of Choi, Rajabi, McKiel, and Kirchmayer teaches or suggests the non-transitory computer-readable medium of claim 18 wherein modifying the editable text object comprises modifying the editable text object via one or more transformation operations in accordance with the depth perspective of the digital raster image (Rajabi, ¶ 0064: teaches OCR tools can identify and store text within a 2D image as editable characters and providing new text within a 3D object; Examiner notes the skilled artisan has in their possession OCR technology allowing for editable text and further notes that text as objects is a conventional computer graphics feature; McKiel, ¶ 0121: teaches the text box is a text object within the 3D environment, which can be obviously manipulated within the environment using a geometric transformation so as to move the text box and potentially project it onto a surface).
Claims 5, 8–10, 12, and 14 are rejected under 35 U.S.C. 103 as being unpatentable over Choi, Rajabi, McKiel, Nagano, and The CG Essentials, “How to Use the SHRINKWRAP Modifier in Blender for Beginners!,” January 31, 2022, YouTube, https://www.youtube.com/watch?v=YksPYPa05LM, accessed 02/26/2026 (herein “CG Essentials”).
Regarding claim 5, the combination of Choi, Rajabi, McKiel, Nagano, and CG Essentials teaches or suggests the computer-implemented method of claim 4, wherein generating the two-dimensional representation of the text region comprises: generating, utilizing a three-dimensional rendering engine, a rendered mesh of the digital raster image (Nagano, ¶ 0049: teaches generating a 3D mesh from a single 2D image; Examiner notes this is a known feature in this art; see references cited under the Conclusion Section of this Office Action; also consider Meta’s SAM3D); aligning a center of the text region with a camera view direction of the digital raster image (Choi, ¶ 0185 and Fig. 1: teaches the alignment of the text in the center of the camera view being accomplished by, for example, a rotation and translation process according to a camera view direction); and projecting the text region aligned with the camera view direction onto the two-dimensional surface using surface normal of the three-dimensional mesh structure and a reverse texture mapping model (Choi, Abstract, ¶ 0081, and e.g. Fig. 1: teaches performing a perspective transformation on a curved surface of a 3D object to flatten the surface for purposes of generating a 2D surface; Compare Applicant’s Fig. 2; Examiner notes UV maps are a flattened region of texture from a 3D mesh and can be extracted or applied from/to the mesh structure using e.g. surface normals (see e.g. Ritter, cited under the Conclusion Section of this Office Action); Examiner finds editable text as a texture applied to the surface of a mesh object is well-represented in this art; see e.g. videos and forum threads cited under the Conclusion Section of this Office Action; see also Choi, Fig. 1, Element 130: illustrating the projection of the text onto a 2D plane).
One of ordinary skill in the art, before the effective filing date of the claimed invention, would have been motivated to combine the elements taught by Choi, Rajabi, McKiel, and Nagano, with those of CG Essentials, because both Choi and CG Essentials are drawn to the same field of endeavor such that one wishing to practice projection from/to a 3D mesh from/to a 2D image plane would be led to their relevant teachings regarding projection/perspective transformation and because reversing Choi’s projection from a 3D object to a 2D plane in the manner described by CG Essentials wherein the 2D plane is projected back onto the 3D object is an obvious workflow for computer graphics designers such that the combination represents a mere combination of prior art elements, according to known methods, to yield a predictable result. This rationale applies to all combinations of Choi, Rajabi, McKiel, Nagano, and CG Essentials used in this Office Action unless otherwise noted.
Regarding claim 8, the combination of Choi, Rajabi, McKiel, Nagano, and CG Essentials teaches or suggests a system comprising: one or more memory devices; and one or more processing devices configured to cause the system to: generate a three-dimensional mesh structure from a digital raster image that portrays a text segment comprising non-editable text in accordance with a depth perspective (Nagano, ¶ 0049: teaches generating a 3D mesh from a single 2D image; Examiner notes this is a known feature in this art; see references cited under the Conclusion Section of this Office Action; also consider Meta’s SAM3D); flatten a text region comprising the text segment by projecting the text region onto a two-dimensional surface using the three-dimensional mesh structure (Choi, Abstract, ¶ 0081, and e.g. Fig. 1: teaches performing a perspective transformation on a curved surface of a 3D object to flatten the surface for purposes of generating a 2D surface; See also Choi, Fig. 9A: demonstrating the text fields recognized as objects on the label; Compare Applicant’s Fig. 2; Choi, e.g. Fig. 3 and ¶ 0272: teach the image(s) are 2D digital raster images taken, for example, by a conventional camera; see also McKiel, infra, describing the surface text object projected onto an object manifold in the image being a raster or bitmap; Examiner further notes UV maps are a flattened region of texture from a 3D mesh and can be extracted or applied from/to the mesh structure using e.g. surface normals; Examiner finds editable text as a texture applied to the surface of a mesh object is well-represented in this art; see e.g. videos and forum threads cited under the Conclusion Section of this Office Action; In a workflow, a 2D raster image can be converted to a mesh and then the workflow can proceed from there utilizing conventional texture maps and conventional text editing of text objects; Indeed, original claim 3 explains the workflow includes converting the 2D raster image into a 3D mesh); generate, using an optical character recognition model and from the projected text region, an editable text object for the text segment having editable text generated from the non-editable text of the text segment (Choi, ¶¶ 0133, 0138, and 0175: teach that once the region of interest is flattened, OCR can be used for extracting information from the region (e.g. label); Compare Applicant’s Fig. 2; Rajabi, ¶ 0064: teaches OCR tools can identify and store text within a 2D image as editable characters and providing new text within a 3D object; Examiner notes the skilled artisan has in their possession OCR technology allowing for editable text and further notes that text as objects is a conventional computer graphics feature); modify the editable text of the editable text object in response to receiving one or more user interactions via a client device portraying the digital raster image (Rajabi, ¶ 0064: teaches OCR tools can identify and store text within a 2D image as editable characters and providing new text within a 3D object); and project the modified editable text object onto the three-dimensional mesh structure to portray the modified editable text object in accordance with the depth perspective of the digital raster image (Projecting a 2D image texture onto the surface of a 3D mesh, for example as a UV map, is well-represented in this art; Choi’s undistort transformation would merely have to be reversed to apply the label back onto the bottle after editing in accordance with the deformation/warp function originally used to flatten the label; Examiner finds Blender’s SHRINKWRAP/projection modifier accomplishes this feature; CG Essentials, Minute 4:57: demonstrates the shrinkwrap modifier using a projection function to create a surface “sticker”.) such that the modified editable text object portrayed in the digital raster image visually conforms to a three-dimensional appearance of at least a portion of the digital raster image (McKiel, ¶ 0121: teaches freely typed text using a text object placed onto the surface of a 3D object and freely changing surface graphics or textures without changing the underlying model; Projecting a 2D image texture onto the surface of a 3D mesh, for example as a UV map, is well-represented in this art; Choi’s undistort transformation would merely have to be reversed to apply the label back onto the bottle after editing in accordance with the deformation/warp function originally used to flatten the label; Examiner finds Blender’s SHRINKWRAP/projection modifier accomplishes this feature; CG Essentials, Minute 4:57: demonstrates the shrinkwrap modifier using a projection function to create a surface “sticker”.).
Regarding claim 9, the combination of Choi, Rajabi, McKiel, Nagano, and CG Essentials teaches or suggests the system of claim 8, wherein the one or more processing devices are further configured to detect the text segment portrayed in accordance with the depth perspective of the digital raster image by using an object detection model to generate one or more outputs that distinguish between one or more text regions of the digital raster image from one or more non-text regions of the digital raster image, wherein at least one text region comprises the text segment (Choi, ¶ 0085: teaches a detection model for extracting information from an ROI of an image; Choi, Fig. 9A: teaches text object detection regions and bounding boxes that distinguish between one or more regions).
Regarding claim 10, the combination of Choi, Rajabi, McKiel, Nagano, and CG Essentials teaches or suggests the system of claim 8, wherein the one or more processing devices are configured to cause the system to generate the three-dimensional mesh structure from the digital raster image: generating, utilizing a depth detection machine learning model, a depth map of the digital raster image (Nagano, ¶¶ 0048 and 0062: teaches auxiliary 3D information, such as depth map data, can be used to aid in the creation of a 3D mesh from a 2D image wherein the depth map is generated using a learning model; see also Nagano, ¶¶ 0064 and 0069: teaching a predicted depth map and a ground truth depth map and the MLP network generating the depth map); generating a three-dimensional mesh of the digital raster image from the depth map of the digital raster image (Nagano, ¶¶ 0048 and 0062: teaches auxiliary 3D information, such as depth map data, can be used to aid in the creation of a 3D mesh from a 2D image); and generating the three-dimensional mesh structure by combining the digital raster image with the three-dimensional mesh of the digital raster image (Nagano, ¶¶ 0048 and 0062: teaches auxiliary 3D information, such as depth map data, can be used to aid in the creation of a 3D mesh from a 2D image).
Regarding claim 12, the combination of Choi, Rajabi, McKiel, Nagano, and CG Essentials teaches or suggests the system of claim 8, wherein projecting the text region onto the two-dimensional surface using the three-dimensional mesh structure comprises: determining one or more surface normals for a portion of the three-dimensional mesh structure corresponding to the text region (Choi, Abstract, ¶ 0081, and e.g. Fig. 1: teaches performing a perspective transformation on a curved surface of a 3D object to flatten the surface for purposes of generating a 2D surface; Compare Applicant’s Fig. 2; Examiner notes UV maps are a flattened region of texture from a 3D mesh and can be extracted or applied from/to the mesh structure using e.g. surface normal (see e.g. Ritter, cited under the Conclusion Section of this Office Action); Examiner finds editable text as a texture applied to the surface of a mesh object is well-represented in this art; see e.g. videos and forum threads cited under the Conclusion Section of this Office Action; see also Choi, Fig. 1, Element 130: illustrating the projection of the text onto a 2D plane); adjusting an orientation of the three-dimensional mesh structure such that a center of the text region aligns with a camera view direction of the digital raster image (Choi, ¶ 0185 and Fig. 1: teaches the alignment of the text in the center of the camera view being accomplished by, for example, a rotation and translation process according to a camera view direction); and projecting, using a reverse texture mapping model, the text region aligned with the camera view direction onto the two-dimensional surface (Choi, Abstract, ¶ 0081, and e.g. Fig. 1: teaches performing a perspective transformation on a curved surface of a 3D object to flatten the surface for purposes of generating a 2D surface; Compare Applicant’s Fig. 2; Examiner notes UV maps are a flattened region of texture from a 3D mesh and can be extracted or applied from/to the mesh structure using e.g. surface normal (see e.g. Ritter, cited under the Conclusion Section of this Office Action); Examiner finds editable text as a texture applied to the surface of a mesh object is well-represented in this art; see e.g. videos and forum threads cited under the Conclusion Section of this Office Action; see also Choi, Fig. 1, Element 130: illustrating the projection of the text onto a 2D plane).
Regarding claim 14, the combination of Choi, Rajabi, McKiel, Nagano, and CG Essentials teaches or suggests the system of claim 8, further comprising generating a modified digital raster image by repositioning the modified editable text object at a second region of the digital raster image that differs from the text region comprising the text segment in accordance with the depth perspective at the second region (Examiner finds a text object can be repositioned within 3D environment or a 2D image; CG Essentials, Minute 6:00: teaches a projection can be along any dimension in the 3D environment, such texture text object being able to be repositioned according to user command).
Claim 13 is rejected under 35 U.S.C. 103 as being unpatentable over Choi, Rajabi, McKiel, Nagano, CG Essentials, and Ghazvinian Zanjani (US 2024/0386650 A1).
Regarding claim 13, the combination of Choi, Rajabi, McKiel, Nagano, CG Essentials, and Ghazvinian Zanjani teaches or suggests the system of claim 12, further comprising determining, using a neural network, at least one camera property associated with the digital raster image (Choi, ¶ 0105: teaches camera properties can be used as parameters for 3D information of an object; Ghazvinian Zanjani, ¶¶ 0076–0077 and 0081: teaches the parameters of the camera and the normal vector from a normal map are used for determining planar depth and finding a correspondence between the 2D input image and the 3D point wherein the normal vector is determined based on camera pose), wherein determining the one or more surface normals for the portion of the three-dimensional mesh structure comprises determining the one or more surface normals using the at least one camera property (Choi, ¶ 0105: teaches camera properties can be used as parameters for 3D information of an object; Ghazvinian Zanjani, ¶¶ 0076–0077 and 0081: teaches the parameters of the camera and the normal vector from a normal map are used for determining planar depth and finding a correspondence between the 2D input image and the 3D point wherein the normal vector is determined based on camera pose).
One of ordinary skill in the art, before the effective filing date of the claimed invention, would have been motivated to combine the elements taught by Nagano, Choi, Rajabi, and CG Essentials, with those of Ghazvinian Zanjani, because at least Nagano and Ghazvinian Zanjani are drawn to the same field of endeavor such that one wishing to practice projection from/to a 3D mesh from/to a 2D image plane would be led to their relevant teachings regarding projection/perspective transformation and because, as Ghazvinian Zanjani teaches, determining a surface normal map aids in 3D reconstruction and such a map can be advantageously, in a 2D image input scenario, be constructed using camera property information. Therefore the combination represents a mere combination of prior art elements, according to known methods, to yield a predictable result. This rationale applies to all combinations of Nagano, Choi, Rajabi, CG Essentials, and Ghazvinian Zanjani used in this Office Action unless otherwise noted.
Claim 11 is rejected under 35 U.S.C. 103 as being unpatentable over Choi, Rajabi, McKiel, Nagano, CG Essentials, and Varekamp (US 2020/0177868 A1).
Regarding claim 11, the combination of Choi, Rajabi, McKiel, Nagano, CG Essentials, and Varekamp teaches or suggests the system of claim 10, wherein generating the three-dimensional mesh of the digital raster image from the depth map comprises: extracting a set of sample points from the depth map of the digital raster image based on a depth variation of the depth map (Varekamp, ¶¶ 0165 and 0167: teach conversion of a depth map to a mesh based on variation of the depth map to generate a triangle mesh; Varekamp, ¶¶ 0015 and 0113: teaches mapping a 2D texture map onto the 3D mesh); and generating a triangle mesh from the set of sample points (Examiner notes triangle meshes represent facets of an object along a depth dimension in 3D space; Nagano, ¶¶ 0048 and 0062: teaches auxiliary 3D information, such as depth map data, can be used to aid in the creation of a 3D mesh from a 2D image).
One of ordinary skill in the art, before the effective filing date of the claimed invention, would have been motivated to combine the elements taught by Choi, Rajabi, McKiel, Nagano, and CG Essentials, with those of Varekamp, because both Nagano and Varekamp are drawn to generating a 3D representation from a 2D input image and because the skilled artisan would look to Varekamp’s teaching of how to generate a triangle mesh utilizing depth map variance to achieve Nagano’s generation of a 3D mesh given both references are drawn to solving the problem of converting a 2D input image into a 3D mesh such that their combination represents a mere combination of prior art elements, according to known methods, to yield a predictable result. This rationale applies to all combinations of Choi, Rajabi, McKiel, Nagano, CG Essentials, and Varekamp used in this Office Action unless otherwise noted.
Claim 20 is rejected under 35 U.S.C. 103 as being unpatentable over Nagano, Choi, Rajabi, McKiel, and Kirchmayer.
Regarding claim 20, the combination of Nagano, Choi, Rajabi, McKiel, and Kirchmayer teaches or suggests the non-transitory computer-readable medium of claim 15, further comprising determining a three-dimensional mesh structure of the digital raster image by: generating, utilizing a machine learning model, a depth map of the digital raster image (Nagano, ¶¶ 0048 and 0062: teaches auxiliary 3D information, such as depth map data, can be used to aid in the creation of a 3D mesh from a 2D image wherein the depth map is generated using a learning model; see also Nagano, ¶¶ 0064 and 0069: teaching a predicted depth map and a ground truth depth map and the MLP network generating the depth map); generating a three-dimensional mesh of the digital raster image based on the depth map of the digital raster image (Nagano, ¶¶ 0048 and 0062: teaches auxiliary 3D information, such as depth map data, can be used to aid in the creation of a 3D mesh from a 2D image); and mapping the digital raster image to the three-dimensional mesh (Nagano, ¶¶ 0048 and 0062: teaches auxiliary 3D information, such as depth map data, can be used to aid in the creation of a 3D mesh from a 2D image), wherein generating the editable text object from the text segment comprises generating the editable text object from the text segment using the three-dimensional mesh structure (Choi, ¶¶ 0133, 0138, and 0175: teach that once the region of interest is flattened, OCR can be used for extracting information from the region (e.g. label); Compare Applicant’s Fig. 2; Rajabi, ¶ 0064: teaches OCR tools can identify and store text within a 2D image as editable characters and providing new text within a 3D object; Examiner notes the skilled artisan has in their possession OCR technology allowing for editable text and further notes that text as objects is a conventional computer graphics feature).
One of ordinary skill in the art, before the effective filing date of the claimed invention, would have been motivated to combine the elements taught by Choi, Rajabi, McKiel, and Nagano, with those of Kirchmayer, because both Choi and Nagano are drawn to the same field of endeavor such that one wishing to practice 3D modeling of objects would be led to their relevant teachings, because Choi’s step of performing a 2D projection of a texture, like text, from a previous generation step like Nagano’s generation of a 3D mesh represents nothing more than a standard computer-graphics workflow or pipeline, because both Choi and Kirchmayer are drawn to the same field of endeavor such that one wishing to practice 3D reconstruction from 2D images (Kirchmayer, e.g. ¶ 0072) would be led to their relevant teachings regarding projection/perspective transformation, and because combining the 3D reconstruction with a hole-filling neural network is an obvious addition to a workflow for computer graphics designers such that the combination represents a mere combination of prior art elements, according to known methods, to yield a predictable result. This rationale applies to all combinations of Choi, Rajabi, McKiel, Nagano, and Kirchmayer used in this Office Action unless otherwise noted.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
derHugo, “Put a text onto a game-object BUT as if it was painted,” Stack Overflow, September 20, 2019, accessed at: https://stackoverflow.com/questions/58021797/put-a-text-onto-a-game-object-but-as-if-it-was-painted. The two images in the supplied .pdf file that show a ball with text are actually videos showing the text dynamically editable on the mesh as a texture.
Jubi, “How to make easily editable text that acts as texture or normal map for another object?,” Blender, 04/30/2014, accessed at https://blender.stackexchange.com/questions/9005/how-to-make-easily-editable-text-that-acts-as-texture-or-normal-map-for-another. This document teaches editable text on the fly without intermediate to-mesh-converting.
The CG Essentials, “How to Use the SHRINKWRAP Modifier in Blender for Beginners!,” January 31, 2022, YouTube, https://www.youtube.com/watch?v=YksPYPa05LM, accessed 02/26/2026. Minute 4:57 demonstrates the shrinkwrap modifier using a projection function to create a surface “sticker”. Minute 8:42 demonstrates the surface normals used for aligning projections on a mesh. Minute 12:30 teaches decals can be wrapped on objects using the shrinkwrap modifier.
Nallamothu (US 2025/0390677 A1) teaches OCR algorithms capable of extracting text from images and converting it to editable texts wherein the text regions are specified using a bounding box (¶ 0031).
Bakshi (US 2026/0025556 A1) teaches an OCR system that converts images into editable text (¶ 0042).
Liu (US 2018/0330480 A1) teaches UV mapping is a process of projecting a 2D image onto a 3D model’s surface using e.g. surface normals (¶ 0167).
M. Liu et al., “One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization,” 37th Conference on Neural Information Processing Systems (NeurIPS 2023).
One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusion,” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024, pp. 10072-10083.
Maxim Tatarchenko, Alexey Dosovitskiy, and Thomas Brox. Multi-view 3d models from single images with a convolutional network. In European Conference on Computer Vision, pages 322-337. Springer, 2016.
Lin (US 2025/0259388 A1) teaches generating a 3D model from a single 2D image (¶ 0096).
Pandian Shanmuganathan (US 2025/0391104 A1) teaches reconstructing a 3D model from 2D images based on machine learning (¶ 0004).
Vircikova (US 2025/0029273 A1) teaches that the art considers 2D image data to include raster images and that 3D data includes meshes (¶¶ 0034–0038).
Gong (US 2023/0368467 A1) teaches using a depth map constructed from a 2D raster image to create a 3D triangle mesh (¶ 0153).
Laddha (US 2025/0308074 A1) teaches, “A 3D triangle mesh is the most common representation for three-dimensional (3D) objects, shapes, and geometry.”
Varekamp (US 2019/0057545 A1) teaches converting a 2D image plus depth map into a 3D triangle mesh utilizing depth variation (¶¶ 0001–0019 and 0021).
Ramsl (US 11,837,000 B1) teaches converting a 2D raster image of an input text character into a 2D vector image and then converting the 2D vector image to a 3D model (e.g. col. 9, ll. 1–14).
Ritter (US 2002/0030681 A1) teaches UV or texture mapping and executing the mapping of a texture onto a plane as defined by its surface normal and wherein the 3D object can be a triangular mesh (e.g. ¶¶ 0028 and 0036).
THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any extension fee pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Michael J Hess whose telephone number is (571)270-7933. The examiner can normally be reached Mon - Fri 9:00am-5:30pm.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, William Vaughn can be reached on (571)272-3922. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8933.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/MICHAEL J HESS/Examiner, Art Unit 2481
Prosecution Insights