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 .
This is in response to Applicant’s Amendments and Remarks filed on 11/7/2025. Claims 2, 4, 5, 7, 9, 1112, 14, 15, 17, 20, and 21 have been amended. Claims 2-21 are present for examination.
The 35 USC 112(b) rejections of claims 4-7, 9, 12, 14, 15, 20, and 21 have been withdrawn in view of the amendments and remarks.
Response to Amendment
The examiner notes that the amendments filed on 11/7/2025 are different than the proposed amendments discussed in the examiner interview conducted 10/21/2025 (see Examiner Interview Summary mailed on 10/23/2025 with Office Action Appendix). Although the examiner indicated that the proposed amendments can overcome the 35 USC 112(b) and 103 rejections, they are not applicable to this Office Action.
Response to Arguments
Applicant's arguments filed 11/7/2025 with respect to the priority have been fully considered but they are not persuasive.
Applicant submits:
PNG
media_image1.png
378
796
media_image1.png
Greyscale
(Remarks filed on 11/7/2025, p. 7.)
The examiner respectfully disagrees. The claims of the current application is about dividing surface into patches and rendering the surface patches. In particular, claim 2 recites:
PNG
media_image2.png
278
776
media_image2.png
Greyscale
Nowhere in the claims have recited lighting.
On the other hand, Provisional Application 63/119,590 discloses “a novel Volumetric Spherical Gaussian representation for lighting, which parametrizes the exitant radiance of the 3D scene surfaces on a voxel grid.” (See 63/119,590, Specification, P. 1, Abstract.) Sec. 3, Lighting Reorientation discloses “to use Volumetric Spherical Gaussian to represent the surface radiance exitant from the full scene, including both visible surfaces and surfaces outside the FoV…Volumetric Spherical Gaussian is a voxel-based representation of a scene” and how to define “the radiance at a viewing angle”. Nowhere in Sec. 3 discusses dividing surface into patches. Figure 2 showing a model overview for monocular inverse rendering consists of 3 modules” using an image as input, but none of the modules discussed dividing a surface into patches. Figure 3 shows lighting predictions from a single image, no surface and/or surface patches have been discussed. Sec. 4 discusses using a single input RGB image to estimate albedo, normal, depth and 3D spatially-varying lighting, and 4.1 again use a single image as input and extracting features for each voxel in the lighting volume. Nowhere in Sec. 4 and 4.1 discusses surface complexity or dividing surface into patches.
Therefore, Provisional Application 63/119,590 has failed to provide adequate support or enablement in the manner provided in 35 USC 112(a) or pre-AIA 35 USC 112, first paragraph for one or more claims of this application.
Applicant’s arguments with respect to claim(s) 2 with respect to 35 USC 103 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
Priority
Applicant’s claim for the benefit of a prior-filed application under 35 U.S.C. 119(e) or under 35 U.S.C. 120, 121, 365(c), or 386(c) is acknowledged. Applicant has not complied with one or more conditions for receiving the benefit of an earlier filing date under 35 U.S.C. 119(e) or 35 U.S.C. 120 as follows:
The later-filed application must be an application for a patent for an invention which is also disclosed in the prior application (the parent or original nonprovisional application or provisional application). The disclosure of the invention in the parent application and in the later-filed application must be sufficient to comply with the requirements of 35 U.S.C. 112(a) or the first paragraph of pre-AIA 35 U.S.C. 112, except for the best mode requirement. See Transco Products, Inc. v. Performance Contracting, Inc., 38 F.3d 551, 32 USPQ2d 1077 (Fed. Cir. 1994).
The disclosure of the prior-filed application, Application No. 63/119,590, fails to provide adequate support or enablement in the manner provided by 35 U.S.C. 112(a) or pre-AIA 35 U.S.C. 112, first paragraph for one or more claims of this application.
Therefore, the effectively filing date regarding the claims of the current application is being considered as 5/7/2021 because the support for the claims in the current application can be found in the parent application 17/314,182 filed on 5/7/2021.
Claim Rejections - 35 USC § 112
The following is a quotation of the first paragraph 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.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
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 of carrying out his invention.
Claims 2-21 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention.
Regarding claim 2, it recites:
A computer-implemented method, comprising: determining that a surface satisfies a complexity threshold or criterion; dividing the surface into a plurality of surface patches corresponding to portions of the surface; determining, using one or more neural networks and based at least in part upon the plurality of surface patches, a plurality of surface patch representations, one or more of the plurality of surface patch representations having a respective specified patch complexity; and rendering the surface using the plurality of surface patch representations. (Emphasis added.)
Applicant submits that Specification, paras. [0022], [0030], and [0057] support this amended limitation. These paragraphs have disclosed level of detail (LOD) using an octree-based feature volume. In particular, para. [0057], discloses the level of detail (LOD) for an object may be determined on a per-frame basis, or at least may vary overtime, and a user or developer may also be able to set values or ranges for levels of detail for certain objects or portions of a scene. However, these paragraphs do not disclose setting LOD for “surface patch representations”, nor do they disclose “one or more of the plurality of surface patch representations having a respective specified patch complexity.” Note, para. [0056], discloses a surface patch by “this complex surface can be divided into a collection of smaller surface patches, where each surface patch represents a portion of the complex surface.” Nowhere in the disclosure discloses “one or more of the plurality of surface patch representations having a respective specified patch complexity”. Therefore, the amended claim 2 contains new matter.
Claims 3-10 depend from claim 2 but fail to cure the deficiencies of claim 2.
Claims 11 and 17 as amended recite similar limitations discussed above with respect to claim 2. Claims 12-16 depend from claim 11 but fail to cure the deficiencies of claim 2. Claims 18-21 depend from claim 17 but fail to cure the deficiencies of claim 17.
Therefore, claims 2-21 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
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) 2-8 and 10-21 is/are rejected under 35 U.S.C. 103 as being unpatentable over US Patent Publication No. 20110046923 A1 to Lee et al. in view of Genova (Genova et al., Local Deep Implicit Functions for 3D Shape) and US Patent Publication No. 20010013866 A1 to Migdal et al.
Regarding claim 2, Lee discloses A computer-implemented method (Lee, para. [0027]), comprising:
determining that a surface satisfies a complexity threshold or criterion (Lee, para. [0051], disclosing subdividing a large 3D mesh model having a complexity value greater than a preset complexity threshold into multiple smaller 3D mesh models);
dividing the surface into a plurality of surface patches corresponding to portions of the surface (Lee, para. [0051], disclosing subdividing a large 3D mesh model having a complexity value greater than a preset complexity threshold into multiple smaller 3D mesh models).
However, Lee does not expressly disclose determining, using one or more neural networks and based at least in part upon the plurality of surface patches, a plurality of surface patch representations, one or more of the plurality of surface patch representations having a respective specified patch complexity; and rendering the surface using the plurality of surface patch representations.
On the other hand, Genova discloses dividing the surface into a plurality of surface patches corresponding to portions of the surface (Genova, Figure 1, showing surfaces are divided into a plurality of shape elements as surface patches corresponding to portions of the surfaces respectively, Figure 2, showing the network architecture starting with a SIF encoder to extract a set of shape elements, then producing a latent vector zi , a local decoder network is used to decode each zi to produce an implicit function fi(x, zi));
determining, using one or more neural networks and based at least in part upon the plurality of surface patches, a plurality of surface patch representations (Genova, p. 4858, col. 1, 2nd para., disclosing LDIF encodes a shape as a latent vector that can be evaluated with a neural network to estimate the inside/outside function f(x,z) for any location x, col. 2, Sec. 3, disclosing a new 3D shape representation, Local Deep Implicit Functions (LDIF) represented by a set of shape elements, Figure 2, showing the network architecture starting with a SIF encoder to extract a set of shape elements, then producing a latent vector zi , a local decoder network is used to decode each zi to produce an implicit function fi(x, zi), which combined with local Gaussian function g(x,θi) and summed with other shape elements to produce the output function LDIF(x), indicating the implicit functions and/or local Gaussian functions can correspond a plurality of surface patch representations determined using the neural networks and based on the shape elements as the plurality of surface patches); and
rendering the surface using the plurality of surface patch representations (Genova, Figure 1, showing resulting implicit surface reconstructed from the input surface and the LDIF, Figure 3, showing the surface rendered using the proposed method of LDIF, p. 4859, col. 2, last para., disclosing complete surfaces can be reconstructed for visualization by evaluating LDIF(x)).
Before the invention was effectively filed, it would have been obvious for a person skilled in the art to combine Lee and Genova. The suggestion/motivation would have been to enable accurate surface reconstruction, compact storage, efficient computation, etc. as suggested by Genova (see Genova, Abstract).
PNG
media_image3.png
208
846
media_image3.png
Greyscale
However, Lee or Genova does not expressly disclose one or more of the plurality of surface patch representations having a respective specified patch complexity.
On the other hand, Migdal discloses one or more of the plurality of surface patch representations having a respective specified patch complexity (Migdal, para. [0044]. Disclosing the user can have varying level of detail refinement selected for different areas of the same mesh model, indicating the areas of the mesh model can correspond to one or more of the plurality of surface patch representations that have user selected level of detail as a respective specified patch complexity).
Before the invention was effectively filed, it would have been obvious for a person skilled in the art to combine Lee in view of Genova with Migdal. The suggestion/motivation would have been for allowing adaptive subdivision of triangulated surfaces, as suggested by Migdal (see Migdal, para. [0042]).
Regarding claim 3, the combination of Lee, Genova, and Midgal discloses the computer-implemented method of claim 2, wherein the surface satisfies the complexity threshold or criterion based on at least one of size, shape, or variation (Lee, para. [0052], disclosing when a 3D mesh model having too many vertices, overload can be experienced, a complexity threshold is set so that a large 3D mesh model having a complexity value greater than the complexity threshold, the large mesh model can be subdivided into multiple smaller 3D mesh models, para. [0053], disclosing the complexity of a 3D mesh model can be determined in correspondence with the number of faces forming the 3D mesh, indicating large 3D mesh model satisfying the complexity threshold can be based on size or variation corresponding to number of faces).
Regarding claim 4, the combination of Lee, Genova, and Midgal discloses the computer-implemented method of claim 2, wherein determining that the surface satisfies the complexity threshold or criterion further comprises: determining the surface satisfies the complexity threshold or criterion for a plurality of frames depicting at least a portion of the surface (Lee, para. [0008], disclosing compressing 3D images such as 3D mesh, para. [0051], disclosing subdivide large 3D mesh model having a complexity value greater than a preset complexity threshold into multiple smaller 3D mesh models, Genova, Figures 1 and 7, showing a plurality of models being decomposed into shape elements and reconstructed using a deep network, indicating the combination of Lee and Genova can determine whether the surface satisfies the complexity threshold or criterion for a plurality of frames corresponding to the input shape depicting at least a portion of the surface). Before the invention was effectively filed, it would have been obvious for a person skilled in the art to combine Lee and Genova. The suggestion/motivation would have been to enable accurate surface reconstruction, compact storage, efficient computation, etc. as suggested by Genova (see Genova, Abstract).
Regarding claim 5, the combination of Lee, Genova, and Midgal discloses the computer-implemented method of claim 2, further comprising: determining, based at least in part on a type of the surface, a complexity of the surface (Lee, para. [0052], disclosing when a 3D mesh model having too many vertices, overload can be experienced, a complexity threshold is set so that a large 3D mesh model having a complexity value greater than the complexity threshold, the large mesh model can be subdivided into multiple smaller 3D mesh models, para. [0053], disclosing the complexity of a 3D mesh model can be determined in correspondence with the number of faces forming the 3D mesh, indicating large 3D mesh model satisfying the complexity threshold can be based on the type of the surface such as large mesh model with large number of faces).
Regarding claim 6, the combination of Lee, Genova, and Midgal discloses the computer-implemented method of claim 5, wherein the complexity of the surface is able to change over time (Lee, para. [0053], disclosing the complexity can be adjusted according to operational environments, indicating the complexity of the surface is able to change over time).
Regarding claim 7, the combination of Lee, Genova, and Midgal discloses the computer-implemented method of claim 2, further comprising: determining a preset complexity is specified for the surface; and applying the preset complexity to the surface for determining that the surface satisfies the complexity threshold or criterion (Lee, para. [0052], disclosing when a 3D mesh model having too many vertices, overload can be experienced, a complexity threshold is set in advance so that a large 3D mesh model having a complexity value greater than the complexity threshold, the large mesh model can be subdivided into multiple smaller 3D mesh models, indicating the complexity threshold as the preset complexity is applied to the mesh model as the surface to determine if the mesh model satisfies the complexity threshold to determine whether to subdivide the large mesh model).
Regarding claim 8, the combination of Lee, Genova, and Midgal discloses the computer-implemented method of claim 2, wherein the determining the plurality of surface patch representations comprises using the one or more neural networks to compute one or more neural signed distance functions (SDFs) for the plurality of surface patches (Genova, p. 4857, col. 2, last para., disclosing training a neural network to estimate the insider/outside or signed-distance function f(x,z) for reconstruction of objects, Figure 2, showing a network structure producing f(x,zi), p. 4860, col. 2, 1st para., disclosing estimating a signed distance function for each training shape including shape elements, indicating the one or more neural networks are used to compute one or more neural signed distance functions (SDFs) for the shape elements corresponding to the plurality of surface patches). Before the invention was effectively filed, it would have been obvious for a person skilled in the art to combine Lee and Genova. The suggestion/motivation would have been to enable accurate surface reconstruction, compact storage, efficient computation, etc. as suggested by Genova (see Genova, Abstract).
Regarding claim 10, the combination of Lee, Genova, and Midgal discloses the computer-implemented method of claim 2, wherein the one or more neural networks are used to represent surfaces other than those used to train the neural networks (Genova, p. 4860, col. 2, Sec. 5, 2nd para., disclosing using ShapeNet dataset, with train and test splits, indicating the test dataset can correspond to surfaces other than the train dataset as those used to train the neural networks). Before the invention was effectively filed, it would have been obvious for a person skilled in the art to combine Lee and Genova. The suggestion/motivation would have been to enable accurate surface reconstruction, compact storage, efficient computation, etc. as suggested by Genova (see Genova, Abstract).
Regarding claim 11, it recites similar limitations of claim 2 but in a system form. The rationale of claim 2 rejection is applied to reject claim 11. In addition, Lee discloses one or more processors (Lee, para. [0051], disclosing an operating unit implemented by a microprocessor).
Regarding claim 12, it recites similar limitations of claim 8 but in a system form. The rationale of claim 8 rejection is applied to reject claim 12. In addition, Lee discloses one or more processors (Lee, para. [0051], disclosing an operating unit implemented by a microprocessor).
Regarding claim 13, it recites similar limitations of claim 3 but in a system form. The rationale of claim 3 rejection is applied to reject claim 13. In addition, Lee discloses one or more processors (Lee, para. [0051], disclosing an operating unit implemented by a microprocessor).
Regarding claim 14, it recites similar limitations of claim 4 but in a system form. The rationale of claim 4 rejection is applied to reject claim 14. In addition, Lee discloses one or more processors (Lee, para. [0051], disclosing an operating unit implemented by a microprocessor).
Regarding claim 15, it recites similar limitations of claim 5 but in a system form. The rationale of claim 5 rejection is applied to reject claim 15. In addition, Lee discloses one or more processors (Lee, para. [0051], disclosing an operating unit implemented by a microprocessor).
Regarding claim 16, the combination of Lee, Genova, and Midgal discloses the system of claim 11, wherein the system comprises at least one of: a system for performing simulation operations; a system for performing simulation operations to test or validate autonomous machine applications; a system for rendering graphical output; a system for performing deep learning operations; a system implemented using an edge device; a system incorporating one or more Virtual Machines (VMs); a system implemented at least partially in a data center; or a system implemented at least partially using cloud computing resources (Genova, p. 4859, col. 1, 2nd para., disclosing using deep network to decode an implicit function, Figures 7-9. Showing surface reconstruction and rendered results, indicating the system can comprise a system for rendering graphical output and/or a system for performing deep learning operations). Before the invention was effectively filed, it would have been obvious for a person skilled in the art to combine Lee and Genova. The suggestion/motivation would have been to enable accurate surface reconstruction, compact storage, efficient computation, etc. as suggested by Genova (see Genova, Abstract).
Regarding claim 17, it recites similar limitations of claim 2 but in a processor form. The rationale of claim 2 rejection is applied to reject claim 17. In addition, Lee discloses a processor having one or more processing units (Lee, para. [0051], disclosing an operating unit implemented by a microprocessor).
Regarding claim 18, it recites similar limitations of claim 8 but in a processor form. The rationale of claim 8 rejection is applied to reject claim 18. In addition, Lee discloses a processor having one or more processing units (Lee, para. [0051], disclosing an operating unit implemented by a microprocessor).
Regarding claim 19, it recites similar limitations of claim 3 but in a processor form. The rationale of claim 3 rejection is applied to reject claim 19. In addition, Lee discloses a processor having one or more processing units (Lee, para. [0051], disclosing an operating unit implemented by a microprocessor).
Regarding claim 20, it recites similar limitations of claim 4 but in a processor form. The rationale of claim 4 rejection is applied to reject claim 20. In addition, Lee discloses a processor having one or more processing units (Lee, para. [0051], disclosing an operating unit implemented by a microprocessor).
Regarding claim 21, it recites similar limitations of claim 5 but in a processor form. The rationale of claim 5 rejection is applied to reject claim 21. In addition, Lee discloses a processor having one or more processing units (Lee, para. [0051], disclosing an operating unit implemented by a microprocessor).
Claim(s) 9 is/are rejected under 35 U.S.C. 103 as being unpatentable over the combination of Lee, Genova, and Midgal as applied to claim 2 above, and further in view of Liu (Liu et al., DIST: Rendering Deep Implicit Signed Distance Function with Differentiable Sphere Tracing).
Regarding claim 9, the combination of Lee, Genova, and Midgal discloses the computer-implemented method of claim 2. However, Lee, Genova, or Migdal does not expressly disclose wherein rendering the surface occurs at an interactive frame rate.
On the other hand, Liu discloses rendering the surface occurs at an interactive frame rate (Liu, p. 3, col. 1, Sec. 3, 1st para., disclosing rendering for implicit signed distance function represented as a neural network, p. 5, col. 2, Sec. 4.1, 1st para., disclosing rendering an image within 0.99s, indicating rendering an image of a surface model can occur at an interactive frame rate).
Before the invention was effectively filed, it would have been obvious for a person skilled in the art to combine the combination of Lee, Genova, and Midgal with Liu. The suggestion/motivation would have been to enable efficient differentiable rendering on the implicit signed distance function represented as a neural network, as suggested by Liu (see Liu p. 2, col. 1, last para.).
Conclusion
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 HAIXIA DU whose telephone number is (571)270-5646. The examiner can normally be reached Monday - Friday 8:00 am-4:00 pm.
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, Kee Tung can be reached at 571-272-7794. 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.
/HAIXIA DU/Primary Examiner, Art Unit 2611