DETAILED ACTION
Response to Arguments
Applicant's arguments filed 07/06/2026 regarding the 35 USC 103 rejections with respect to the amended limitations of claims 1-20 “generate, at inference time, a point cloud associated with the object based at least in part on the image embedding;” in pages 8-9 against Gupta, have been considered but are moot in view of the new ground(s) of rejection necessitated by the amendment. However Gupta is cited as a secondary reference to include the features of generating a textured mesh based on triplane (abstract, Fig 1) in the current office action, that is applied once the triplane is available.
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1-3, 11-12, 14, 16-18 are rejected under 35 U.S.C. 103 as being unpatentable over Zou et al (Zou, Zi-Xin, Zhipeng Yu, Yuan-Chen Guo, Yangguang Li, Ding Liang, Yan-Pei Cao, and Song-Hai Zhang. "Triplane meets gaussian splatting: Fast and generalizable single-view 3d reconstruction with transformers." In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 10324-10335. 2024.), and further in view of Gupta et al (Gupta A, Xiong W, Nie Y, Jones I, Oğuz B. 3dgen: Triplane latent diffusion for textured mesh generation. arXiv preprint arXiv:2303.05371. 2023 Mar 9.).
RE claim 1, Zou teaches A system comprising: one or more storage media storing instructions; and one or more processors configured to execute the instructions (Abstract, Fig 2 illustrating typical computer system comprising memory and processor) to cause the system to:
generate an image embedding based at least in part on an object (Abstract, Figs 1-2, page 10327 col 1, page 10328 col 1);
generate, at inference time, a point cloud associated with the object based at least in part on the image embedding (Abstract, Figs 1-2, page 10327 col 1, page 10328 col 1);
generate a triplane embedding representing the object based at least in part on the image embedding and the point cloud (Abstract, Figs 1-2, page 10327 col 1, page 10328 col 1); and
generate, based at least in part on the triplane embedding a first texture for the object (Abstract, Figs 1-2, page 10327 col 2, page 10330 col 1).
Zou is silent RE: at least one of a first three-dimensional mesh associated with the object or the first texture for the first three-dimensional mesh.
However Gupta teaches in Abstract, Fig 1, page 1 col 2, page 2 col 2 section 2 and section 2.3 in page 3 col 1 to generate 3D textured mesh from triplane utilizing machine learning.
Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to include in Zou a system and method to generate at least one of a first three-dimensional mesh associated with the object or the first texture for the first three-dimensional mesh, as suggested by Gupta, in order to leverage typical mesh based rendering and thereby ensuring/increasing system effectiveness and user experience.
RE claim 2, Zou as modified by Gupta teaches wherein the execution of the instructions further causes the system to: generate a first scene attribute map based on the triplane embedding, wherein the first scene attribute map encodes illumination data (Zou Fig 2 page 10327 col 2, and Gupta Fig 1, page 3 col 1, and page 4 col 1, page 6 cols 1-2 etc, RGB/color map representing the luminance for each color channels, in addition lighting and shadow maps.).
RE claim 3, Zou as modified by Gupta teaches wherein the execution of the instructions further causes the system to: receive a second scene attribute map, wherein the second scene attribute map is distinct from the first scene attribute map (Zou Fig 1, page 3 col 1, SDF/depth map); and
render the first three-dimensional mesh based at least in part on the second scene attribute map (Zou Fig 2 page 10327 col 2, and Gupta Figs 1, 6, page 3 col 1, page 4 col 1, page 6 col 2).
Claims 11-12 and 16 recite limitations similar in scope with limitations of claims 1-3 as method and therefore rejected under the same rationale.
RE claim 14, Zou as modified by Gupta teaches wherein the point cloud includes less than 20,000 points (Zou page 10328 col 1).
Claims 17-18 recite limitations similar in scope with limitations of claim 1, and therefore rejected under the same rationale. In addition Zou teaches One or more non-transitory computer-readable storage media storing instructions (Abstract, Fig 2 wherein method instructions are typically stored in One or more non-transitory computer-readable storage media)
Claims 4-5, 8, 13 and 15 are rejected under 35 U.S.C. 103 as being unpatentable over Zou as modified by Gupta, and further in view of Good (US 11727640 B1).
RE claim 4, Zou as modified by Gupta teaches wherein the object is presented from a first view (Zou Figs 1-2).
Zou as modified by Gupta is silent RE: and wherein the execution of the instructions further causes the system to present the first three-dimensional mesh from a second view that is different from the first view. However Good teaches in col 10 lines 13-17.
Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to include in Zou as modified by Gupta a system and method to present the first three-dimensional mesh from a second view that is different from the first view, as suggested by Good, in order to allow the view from different perspectives interactively and thereby increasing system effectiveness and user experience.
RE claim 5, Zou as modified by Gupta is silent RE: wherein the point cloud includes at least one albedo value, and wherein generating the first three-dimensional mesh comprises: utilizing the at least one albedo value included in the point cloud as conditioning input for estimating an intrinsic surface color of the object, such that the first three-dimensional mesh includes attributes based at least in part on the at least one albedo value of the point cloud.
However Good teaches in Fig 2, col 3 lines 55-62, and col 4 lines 41-45.
Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to include in Zou as modified by Gupta a system and method to wherein the point cloud includes at least one albedo value, and wherein generating the first three-dimensional mesh comprises: utilizing the at least one albedo value included in the point cloud as conditioning input for estimating an intrinsic surface color of the object, such that the first three-dimensional mesh includes attributes based at least in part on the at least one albedo value of the point cloud, as suggested by Good, in order to provide realistic rendering utilizing albedo value and thereby increasing system effectiveness and user experience.
RE claim 8, Zou as modified by Gupta teaches wherein at least one point included in the point cloud represent a geometric attribute (Zou Abstract, Figs 1-2, page 10327 col 1).
Zou as modified by Gupta is silent RE: an albedo attribute.
However Good teaches in Fig 2, col 3 lines 55-62, and col 4 lines 41-45.
Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to include in Zou as modified by Gupta a system and method an albedo attribute, as suggested by Good, in order to provide realistic rendering utilizing albedo value and thereby increasing system effectiveness and user experience.
RE claim 13, Zou as modified by Gupta is silent RE: wherein the first three- dimensional mesh represents an attribute including at least one of: an albedo attribute, a roughness attribute, or a metallicity attribute.
However Good teaches including in Fig 2, col 3 lines 55-62, and col 4 lines 41-45.
Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to include in Zou as modified by Gupta a system and method wherein the first three- dimensional mesh represents an attribute including at least one of: an albedo attribute, a roughness attribute, or a metallicity attribute, as suggested by Good, in order to provide realistic rendering utilizing the different attribute values and thereby increasing system effectiveness and user experience.
RE claim 15, Zou as modified by Gupta is silent RE: further comprising: receiving one or more signals from a user interface that indicate a modification to the point cloud; modifying the point cloud based on the one or more signals to generate a modified point cloud; and generating at least one of: (i) a second three-dimensional mesh associated with the object, (ii) or a second texture based at least in part on the modified point cloud, wherein the second three-dimensional mesh is different from the first three-dimensional mesh and the second texture is different than the first texture.
However Good teaches in Figs 1-3, 10, col 10 lines 11-26.
Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to include in Zou as modified by Gupta a system and method of receiving one or more signals from a user interface that indicate a modification to the point cloud; modifying the point cloud based on the one or more signals to generate a modified point cloud; and generating at least one of: (i) a second three-dimensional mesh associated with the object, (ii) or a second texture based at least in part on the modified point cloud, wherein the second three-dimensional mesh is different from the first three-dimensional mesh and the second texture is different than the first texture., as suggested by Good, in order to different views interactively and thereby increasing system effectiveness and user experience.
Claim 6 is rejected under 35 U.S.C. 103 as being unpatentable over Zou as modified by Gupta, and further in view of Qian et al (US 20170200309 A1) and Janzer et al (US 20180122139 A1).
RE claim 6, Zou as modified by Gupta is silent RE wherein generating a rendering based at least in part on the first three-dimensional mesh associated with the object comprises execution of the instructions to further cause the system to: project a ray onto a surface point of the first three-dimensional mesh; compare a depth of the ray with a depth map associated with the first three-dimensional mesh; determine, based at least in part on the comparison, the ray is occluded by a portion of the first three-dimensional mesh, wherein the portion is closer to the ray than the surface point along a direction of the ray; and modify the rendering, the modification comprising modifying an illumination of the surface point based at least in part on the determination the ray is occluded.
However Qian teaches wherein generating a rendering based at least in part on the first three-dimensional mesh associated with the object comprises execution of the instructions to further cause the system to: project a ray onto a surface point of the first three-dimensional mesh; compare a depth of the ray with a depth map associated with the first three-dimensional mesh; determine, based at least in part on the comparison, the ray is occluded by a portion of the first three-dimensional mesh, wherein the portion is closer to the ray than the surface point along a direction of the ray in Figs 3, 5-7, [0034]-[0035], [0050], [0046]. In addition Janzer teaches modify the base UV map with an item UV map using the representation of occluded areas on the base asset 0102].
Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to include in Zou as modified by Gupta a system and method wherein generating a rendering based at least in part on the first three-dimensional mesh associated with the object comprises execution of the instructions to further cause the system to: project a ray onto a surface point of the first three-dimensional mesh; compare a depth of the ray with a depth map associated with the first three-dimensional mesh; determine, based at least in part on the comparison, the ray is occluded by a portion of the first three-dimensional mesh, wherein the portion is closer to the ray than the surface point along a direction of the ray; and modify the rendering, the modification comprising modifying an illumination of the surface point based at least in part on the determination the ray is occluded, combining the teachings of Qian and Janzer, in order to provide occlusion correction and enhance the rendering and thereby increasing system effectiveness and user experience.
Claims 7, 19-20 are rejected under 35 U.S.C. 103 as being unpatentable over Zou as modified by Gupta, and further in view of Kreis et al (US 20240005604 A1).
RE claim 7, Zou as modified by Gupta teaches wherein the execution of the instructions further causes the system to: generate an image token embedding based at least in part on inputting the image embedding to an embedding projection system; and generate the triplane embedding representing the object based at least in part on inputting the image token embedding and denoised point cloud embedding to a transformer model (Zou Fig 2 page 10327 col 1, and Gupta Abstract, Fig 1, page 1 col 2, page 2 col 2 section 2 and section 2.3 in page 3 col 1).
Zou as modified by Gupta is silent RE: generate a denoised point cloud embedding based at least in part on inputting a denoised point cloud to a denoised point cloud embedding system.
However Kreis teaches [0023], [0028], [0034] to generate a denoised point cloud utilizing machine learning.
Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to include in Zou as modified by Gupta a system and method to Kreis, as suggested by Kreis, in order to generate accurate point cloud and thereby increasing system effectiveness and user experience.
Claim 17 recites limitations similar in scope with limitations of claim 7 and therefore rejected under the same rationale. In addition Zou as modified by Gupta and Kreis teaches generating a noisy point cloud embedding based at least in part on inputting a noisy point cloud to a point cloud embedding system; generating a combined embedding based at least in part on combining the image token embedding and the noisy point cloud embedding (Kreis [0023], [0028], [0034]).
RE claim 20, Zou as modified by Gupta and Kreis teaches wherein the image token embedding and the noisy point cloud embedding are dimensionally aligned by projecting the image embedding and the noisy point cloud embedding to a common dimension (Zou Fig 2 page 10327 cols 1-2, Gupta Abstract, Fig 1, page 2 col 2-page 3 col 2, details of generating the embedding and alignment features with the triplane and image tokens (laten codes)).
Claims 9-10 rejected under 35 U.S.C. 103 as being unpatentable over Zou as modified by Gupta, and further in view of Bradley et al (US 20230154101 A1).
RE claim 9, Zou as modified by Gupta teaches wherein the execution of the instructions further causes the system to: generate an attribute embedding based at least in part on inputting the triplane embedding to a scene attribute encoder (Zou Fig 2 page 10327 cols 1-2, Gupta Abstract, Fig 1, page 1 col 2, page 2 col 2 section 2).
Zou as modified by Gupta is silent RE: wherein the attribute embedding comprises at least one albedo value; and generate the first scene attribute map based at least in part on inputting the attribute embedding to a scene attribute decoder.
However Bradley teaches Fig 3, [0047] as part of texture generation utilizing machine learning.
Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to include in Zou as modified by Gupta a system and method to wherein the attribute embedding comprises at least one albedo value; and generate the first scene attribute map based at least in part on inputting the attribute embedding to a scene attribute decoder, as suggested by Bradley, in order to provide realistic rendering utilizing albedo value and thereby increasing system effectiveness and user experience.
RE claim 10, Zou as modified by Gupta teaches wherein the execution of the instructions further causes the system to: generate one or more attribute features based at least in part on inputting the triplane embedding or the image embedding into a respective attribute determination system, wherein the one or more attribute features encode an attribute associated with the object (Zou Fig 2 page 10327 cols 1-2, Gupta Abstract, Fig 1, page 1 col 2, page 2 col 2 section 2).
Zou as modified by Gupta is silent RE: generate a density field based at least in part on inputting the one or more attribute features to a density field generation system; and generate the first three-dimensional mesh based at least in part on inputting at least one of the density field or the one or more attribute features to a mesh construction system.
However Bradley teaches in Fig 3, [0047] as part of texture generation utilizing machine learning.
Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to include in Zou as modified by Gupta a system and method to generate a density field based at least in part on inputting the one or more attribute features to a density field generation system; and generate the first three-dimensional mesh based at least in part on inputting at least one of the density field or the one or more attribute features to a mesh construction system, as suggested by Bradley, in order to provide realistic rendering utilizing density value and thereby increasing system effectiveness and user experience.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. See attached 892.
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). 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 nonprovisional extension fee (37 CFR 1.17(a)) 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 SULTANA MARCIA ZALALEE whose telephone number is (571)270-1411. The examiner can normally be reached Monday- Friday 8:00am-4:30pm.
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, Kent Chang can be reached at (571)272-7667. 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.
/Sultana M Zalalee/ Primary Examiner, Art Unit 2614
Prosecution Insights