DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 05/22/2026 has been entered.
Application Status
This office action is responsive to the claim amendments filed on 05/15/2026.
Claims 1-21 are pending and presented for examination.
The 35 USC 112 rejection is withdrawn in view of the Applicant’s amendments.
The 35 USC 101 rejection is withdrawn in view of the Applicant’s amendments.
This action has been made NON-FINAL.
Response to Arguments
Applicant's arguments filed 05/15/2026 have been fully considered but they are not persuasive.
The Applicant alleged the following on pages 10-13 of the remarks: “Claim 1 stands rejected under 35 U.S.C. § 102 as being anticipated by Gausebeck. Applicant respectfully disagrees. The cited sections of Gausebeck describe using a neural network to generate a 3D model from multiple 2D images stitched together. See Gausebeck at 7:9-55. Gausebeck further describes that once the 3D model is generated, textual data (e.g., names) can be associated with different parts of the 3D model (e.g., rooms). See id., at 19:5-15. For example, each room in the 3D model can have its own textual description (e.g., name). See id. However, Gausebeck does not 1) generate a 3D model of an object based on one or more text prompts describing the object, 2) use the generated 3D model to then generate multiple images of the one or more objects from different viewpoints, and 3) update the 3D model based on whether the generated multiple images collectively correspond to the one or more text prompts. Rather, Gausebeck generates a 3D model of the same object from the stitched 2D images. See id., at 7:9- 55. Further, the textual description described in Gausebeck is related to naming conventions (e.g., bedroom, bathroom) applied after the 3D model is generated, whereas the claim recites using textual prompts to generate the 3D model in the first place. Therefore, it cannot be said that Gausebeck anticipates claim 1.” The examiner is not persuaded. Gausebeck teachings in Column 19, Lines 5-15 reciting “3D floorplan model” correlates to the Applicant’s claim language of 1) “generate a 3D model of an object based on one or more text prompts describing the object.” Gausebeck teachings in Column 11, Lines 35-45 and Column 19, Lines 5-15 correlates to the Applicant’s claim language of 2) “use the generated candidate 3D model to generate multiple images of the one or more objects from different viewpoints.” Moreover, Gausebeck teachings in Column 61, Lines 10-30 of “the 3D reconstruction can comprise a first or initial 3D reconstruction, and wherein based on reception of the confirmation message, the remote device can generate a second (or final) 3D reconstruction of the object or environment. For example, in some implementations, the second 3D reconstruction has a higher level of image quality relative to the first three-dimensional reconstruction. In another example, implementation, the second 3D reconstruction comprises a navigable model of the environment and wherein the first 3D reconstruction is not navigable. In another example implementation, the second 3D reconstruction was generated using a more precise alignment process relative to an alignment process used to generate the first 3D reconstruction” correlates to the Applicant’s teachings of 3) “update the 3D model based on whether the generated multiple images collectively correspond to the one or more text prompts.” MPEP § 2106 states Office personnel are to give claims their broadest reasonable interpretation in light of the supporting disclosure. In re Morris, 127 F.3d 1048, 1054-55, 44 USPQ2d 1023, 1027-28 (Fed Cir. 1997). Accordingly, the examiner maintains the rejection.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claim(s) 1, 2, 7-9, 14-16 and 20-21 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Gausebeck, US Patent No.: 11,094,137.
Claim 1:
Gausebeck discloses one or more processors (See Gausebeck Column 13, Lines 38-40), comprising:
circuity to:
receive one or more text prompts describing one or more objections (See Gausebeck Column 19, Lines 5-151; Column 63, Lines 1-202);
use one or more neural networks to (See Gausebeck Column 5, Lines 7-24):
generate a candidate three-dimensional (3D) model of the one or more objects (See Gausebeck Column 19, Lines 5-153);
use the generated candidate 3D model (See Gausebeck Column 19, Lines 5-154) to generate multiple images of the one or more objects from different viewpoints (See Gausebeck Column 11, Lines 35-45);
and update the candidate 3D model based (See Gausebeck Column 19, Lines 5-155; Column 61, Lines 10-306), at least in part, on an evaluation by the one or more neural networks (See Gausebeck Column 5, Lines 7-24) of whether the generated multiple images collectively correspond to the one or more text prompts (See Gausebeck Column 19, Lines 5-157; Column 63, Lines 1-208).
Claim 2:
Gausebeck discloses wherein the one or more neural networks (See Gausebeck Column 5, Lines 7-24) are to generate the candidate 3D model based (See Gausebeck Column 19, Lines 5-15), at least in part, on the multiple images (See Gausebeck Column 7, Lines 9-55) as a result of being trained based (See Gausebeck Column 4, Lines 35-50), at least in part, on the multiple images (See Gausebeck Column 7, Lines 9-55) of the one or more objects from the different viewpoints (See Gausebeck Column 11, Lines 35-45).
Claim 7:
Gausebeck discloses wherein the circuitry is to further cause the candidate 3D model to be refined based (See Gausebeck Column 19, Lines 5-15), at least in part, on the one or more textual prompts (See Gausebeck Column 19, Lines 5-15) and the multiple images of the one or more objects (See Gausebeck Column 7, Lines 9-55).
Claims 8-9:
Claims 8-9 are rejected on the same basis as claims 1 and 2.
Claim 14:
Gausebeck discloses wherein the different viewpoints (See Gausebeck Column 11, Lines 35-45) are captured by one or more cameras positioned in locations that are equally spaced apart (See Gausebeck Column 19, Lines 55-65).
Claims 15-16:
Claims 15-16 are rejected on the same basis as claims 1 and 2.
Claim 20:
Gausebeck discloses wherein the different viewpoints (See Gausebeck Column 11, Lines 35-45) are captured by four or more cameras that are equally spaced apart (See Gausebeck Column 19, Lines 55-659).
Claim 21:
Gausebeck discloses wherein one or more parameters of the one or more neural networks (See Gausebeck Column 5, Lines 7-24) is updated based on aligning the candidate 3D model with the multiple images (See Gausebeck Column 7, Lines 9-55).
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, 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.
Claim(s) 3, 10, and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Gausebeck US Patent No.: 11,094,137 in view of Cowan, US Patent No.: 11,610,284.
Claim 3:
Gausebeck failed to discloses loss measurements. However, Cowan discloses this feature in Column, Lines 28-65. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to have further modified Gausebeck by the teachings of Cowan to enable improved management of neural networks by incorporating generated loss measurements data more effectively (See Cowan Abstract). In addition, the references teach features that are directed to analogous art and they are directed to the same field of endeavor. This close relation between both of the references highly suggests an expectation of success.
As modified:
The combination of Gausebeck and Cowan discloses the following:
wherein the one or more neural networks (See Gausebeck Column 5, Lines 7-24) are trained based, at least in part, on one or more loss measurements (See Cowan Column, Lines 28-65) corresponding to a comparison of the candidate 3D model of the one or more objects (See Gausebeck Column 19, Lines 5-15) from the different viewpoints (See Gausebeck Column 11, Lines 35-45) with the multiple images of the one or more objects (See Gausebeck Column 7, Lines 9-55).
Claims 10 and 17:
Claims 10 and 17 are rejected on the same basis as claim 3.
Claims 4-6, 11-13, 18 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Gausebeck US Patent No.: 11,094,137 in view of Cowan, US Patent No.: 11,610,284 and in further view of Kharbanda, US Patent No.: 12266065.
Claim 4:
The combination of Gausebeck and Cowan failed to discloses a collage of images. However, Kharbanda discloses this feature in Column 24, Lines 15-25 and Lines 40-55. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to have further modified Gausebeck and Cowan by the teachings of Kharbanda to enable improved management of neural networks by improving generated data by incorporating a collage of images, more effectively (See Kharbanda Abstract). In addition, the references teach features that are directed to analogous art and they are directed to the same field of endeavor. This close relation between both of the references highly suggests an expectation of success.
As modified:
The combination of Gausebeck, Cowan and Kharbanda discloses the following:
wherein the multiple images (See Gausebeck Column 7, Lines 9-55) of the one or more objects from the different viewpoints (See Gausebeck Column 11, Lines 35-45) are combined into a collage of images (See Kharbanda Column 24, Lines 15-25 and Lines 40-55) that are used to train the one or more neural networks (See Gausebeck Column 5, Lines 7-24).
Claim 5:
The combination of Gausebeck and Cowan failed to discloses diffusion models. However, Kharbanda discloses this feature in Column 35, Lines 50-67. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to have further modified Gausebeck and Cowan by the teachings of Kharbanda to enable improved management of neural networks by improving generated data by incorporating modeling, more effectively (See Kharbanda Abstract). In addition, the references teach features that are directed to analogous art and they are directed to the same field of endeavor. This close relation between both of the references highly suggests an expectation of success.
As modified:
The combination of Gausebeck, Cowan and Kharbanda discloses the following:
wherein the one or more neural networks (See Gausebeck Column 5, Lines 7-24) comprise one or more diffusion models (See Kharbanda Column 35, Lines 50-67).
Claim 6:
The combination of Gausebeck, Cowan and Kharbanda discloses wherein the multiple images of the one or more objects (See Gausebeck Column 7, Lines 9-55) from the different viewpoints (See Gausebeck Column 11, Lines 35-45) are in a collage of images (See Kharbanda Column 24, Lines 15-25 and Lines 40-55) used to fine-tune a two-dimensional (2D) diffusion model (See Kharbanda Column 35, Lines 50-67).
Claims 11-12:
Claims 11-12 are rejected on the same basis as claims 4-5.
Claim 13:
The combination of Gausebeck, Cowan and Kharbanda discloses wherein the one or more processors (See Gausebeck Column 13, Lines 38-40) randomly sample one or more camera viewpoints (See Gausebeck Column 11, Lines 35-45) with fixed relative angle offsets to render images based on a three-dimensional (3D) Computer-Aided Design (CAD) model (See Gausebeck Column 66, Lines 4-10) to generate an image collage (See Kharbanda Column 24, Lines 15-25 and Lines 40-55) to train the one or more neural networks (See Gausebeck Column 5, Lines 7-24).
Claim 18:
Claim 18 is rejected on the same basis as claim 4.
Claim 19:
The combination of Gausebeck and Cowan failed to disclose a text-to-image diffusion model. However, Kharbanda discloses this feature in Column 35, Lines 50-67. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to have further modified Gausebeck and Cowan by the teachings of Kharbanda to enable improved management of neural networks by improving generated data by incorporating modeling, more effectively (See Kharbanda Abstract). In addition, the references teach features that are directed to analogous art and they are directed to the same field of endeavor. This close relation between both of the references highly suggests an expectation of success.
As modified:
The combination of Gausebeck, Cowan and Kharbanda discloses the following:
wherein the one or more neural networks (See Gausebeck Column 5, Lines 7-24) comprise a text-to-image diffusion model (See Kharbanda Column 35, Lines 50-67).
Pertinent Art
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
US 20240386685 relates to relate generally to natural language processing and machine learning systems, and more specifically to systems and methods for reconstructing a three-dimensional (3D) object from a two-dimensional (2D) image.
Contact Information
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SHEREE N BROWN whose telephone number is (571)272-4229. The examiner can normally be reached M-F 5:30-2:00 PM EST.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, SAID BROOME can be reached at (571) 272-2931. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/SHEREE N BROWN/Primary Examiner, Art Unit 2612 June 12, 2026
1 Gausebeck Column 19, Lines 5-15 recites “a textual data.”
2 Gausebeck Column 63, Lines 1-20 recites “the AR data objects 3022 can include icons, text, symbols tags, hyperlinks etc. that can be visually displayed and interacted with. In another example, the AR data objects 3022 can include data objects that are not visually displayed (or initially visually displayed) but can be interacted with and/or are activated in response to a trigger (e.g., a user pointing at, viewing in line of sight of the user, a gesture etc.). For example, in one embodiment involving, based on viewing or pointing to an actual object appearing in the environment, (e.g., a building), auxiliary data can be rendered that is associated with the building, such as text overlay identifying the building, video data, sound data, graphical image data corresponding to an object or thing emerging from an open window of the building, etc.”
3 Gausebeck Column 19, Lines 5-15 recites “3D floorplan model.”
4 Gausebeck Column 19, Lines 5-15 recites “3D floorplan model.”
5 Gausebeck Column 19, Lines 5-15 recites “3D floorplan model.”
6 Gausebeck Column 61, Lines 10-30 “the 3D reconstruction can comprise a first or initial 3D reconstruction, and wherein based on reception of the confirmation message, the remote device can generate a second (or final) 3D reconstruction of the object or environment. For example, in some implementations, the second 3D reconstruction has a higher level of image quality relative to the first three-dimensional reconstruction. In another example, implementation, the second 3D reconstruction comprises a navigable model of the environment and wherein the first 3D reconstruction is not navigable. In another example implementation, the second 3D reconstruction was generated using a more precise alignment process relative to an alignment process used to generate the first 3D reconstruction.”
7 Gausebeck Column 19, Lines 5-15 recites “a textual data.”
8 Gausebeck Column 63, Lines 1-20 recites “the AR data objects 3022 can include icons, text, symbols tags, hyperlinks etc. that can be visually displayed and interacted with. In another example, the AR data objects 3022 can include data objects that are not visually displayed (or initially visually displayed) but can be interacted with and/or are activated in response to a trigger (e.g., a user pointing at, viewing in line of sight of the user, a gesture etc.). For example, in one embodiment involving, based on viewing or pointing to an actual object appearing in the environment, (e.g., a building), auxiliary data can be rendered that is associated with the building, such as text overlay identifying the building, video data, sound data, graphical image data corresponding to an object or thing emerging from an open window of the building, etc.”
9 In view of the pending 35 USC 112 rejection, the examiner asserts Gausebeck’s teachings of “using one or more cameras (or one or more camera lenses) provided on the user device 130 or a separate camera, a user can control capturing 2D images of an environment at various positions and/or orientations relative to the environment” in Column 19, Lines 55-65 discloses the Applicant’s claim language.
Prosecution Insights