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 .
Status of the Claims
Claims 1-2, 4-6 and 9-15 are currently pending in the present application, with claims 1 and 11 being independent. Claims 16-20 are withdrawn from further consideration as being drawn to a non-elected invention.
Response to Amendments / Arguments
Applicant’s arguments, see Pg. 9-12, filed 06/19/2026, with respect to the rejection(s) of claim(s) 1-2, 4-6 and 9-15 under 35 U.S.C. § 103 have been fully considered and are persuasive. Therefore, the rejection has been withdrawn. However, upon further consideration, a new ground(s) of rejection is made in view of newly found prior art.
Regarding the remaining arguments: Applicant argues with respect to the amended claim language, which is fully addressed in the prior art rejections set forth below.
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) 1-2, 4-6, and 10-14 is/are rejected under 35 U.S.C. 103 as being unpatentable over Sun et al. "Direct voxel grid optimization: Super-fast convergence for radiance fields reconstruction." In 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5449-5459. IEEE, 2022, hereinafter referred to as “Sun”, in view of Clark "Volumetric bundle adjustment for online photorealistic scene capture." In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6124-6132. 2022.
Regarding claim 1, Sun discloses a computing device for rendering a model volume data structure (Pg. 5450, Section 1; real-time rendering…use a dense voxel grid to directly model the 3D geometry (volume density) …NVIDIA RTX 2080 Ti GPU), the computing device comprising:
a processor coupled to a storage medium that stores instructions, which, upon execution by the processor (Fig. 1(b); machine with a single NVIDIA RTX 2080 Ti GPU), cause the processor to:
generate the model volume data structure by (Fig. 1; our voxel grid representation is directly and efficiently trained from scratch for each scene):
generating a density volume data structure and a color volume data structure based on at least on a plurality of two-dimensional images of a model (Pg. 43339, Section 1; reconstruct a volumetric scene representation from a set of images, NeRF uses multilayer perceptron (MLP) to implicitly learn the mapping from a queried 3D point (with a viewing direction) to its colors and densities. Pg. 5451, Section 3; Given the training images with known poses, NeRF model is trained by minimizing the photometric MSE between the observed pixel color C(r) and the rendered color C^(r)…Pg. 5453, Section 5.1; We use coarse density voxel grid V(density)(c)… to model scene geometry. We only model view-invariant color emissions V(rgb)(c)…in the coarse stage. Section 5.2; in the fine stage, we use a higher-resolution density voxel grid V(density)(f)…), wherein the density volume data structures stores density values (Pg. 5452, Section 4; A voxel-representation models the modalities of interest (e.g., density, color, or feature) explicitly in its grid cells…Density voxel grid, V(density), is a special case with C = 1, which stores the density values for volume rendering (Eq. (2))) and the color volume data structure stores color features (Pg. 5452, Section 4; A voxel-representation models the modalities of interest (e.g., density, color, or feature) explicitly in its grid cells…Pg. 5453, Section 5.2; Our hybrid representation comprises i) a feature voxel grid V(feat)(f)…,and ii) a shallow MLP…(Eq. (10b))…the view-dependent color emission)), ;
determine a camera view in which to render the model volume data structure (Pg. 43339, Section 1; reconstruct a volumetric scene representation from a set of images, NeRF uses multilayer perceptron (MLP) to implicitly learn the mapping from a queried 3D point (with a viewing direction) to its colors and densities. The queried properties along the camera ray can then be accumulated into a pixel color by volume rendering techniques);
determine a plurality of rays in three-dimensional space based on the camera view (Pg. 5451, Section 3; To render the color of a pixel C^(r), we cast the ray r from the camera center through the pixel…);
for each ray in the plurality of rays, determine a color value by:
determining a plurality of sample points along the ray (Pg. 5453, Section 5.1; On a pixel-rendering ray, we sample query points as…Eq. (8a), (8b) …where o is the camera center, d is the ray-casting direction…the last sampled point stops nearby the far plane); and
querying the density volume data structure to obtain density values corresponding to the plurality of sample points (Pg. 5453, Section 5.1; A query of any 3D point x is efficient with interpolation: Eq. (7a)…the raw volume density. Section 5.2; queries of 3D points x and viewing-direction d are performed by Eq. (10a)…is the raw volume density in the fine stage);
determining a set of valid points from the plurality of sample points based at least upon the density values corresponding to the plurality of sample points (Pg. 5454, Section 5.2; A query point is in the known free space if the post-activated alpha value from the optimized V(density)(c) is less than the threshold τ(c)…First, we skip sampled points that are in the known free space by checking the optimized V(density)(c)…Second, we further skip sampled points in unknown space with low activated alpha value (threshold at τ(f)) by querying V(density)(f)); and
querying the color volume data structure using the set of valid points to determine the color value (Section 5.1; Eq. (7b). Section 5.2; Eq. (10b)); and
render the model volume data structure using the color values of the plurality of rays (Pg. 5451, Section 3; To render the color of a pixel…the K queried results are accumulated into a single color with the volume rendering quadrature…Eq. (2a)…)
Sun does not disclose wherein each of the density volume data structure and the color volume data structure comprises a B+ tree graph.
In the same art of voxel-based volumetric scene representation for novel-view rendering, Clark discloses wherein each of the density volume data structure and the color volume data structure comprises (Fig. 1 and Pg. 6125, Section 1; A neural volumetric dynamic B+Tree, called nVDB, that can efficiently represent 3D scenes and can grow as more areas of the scene are explored. Section 4; Our system takes as input a sequence of images Ii, a rough estimate of the depth Di at each frame and camera poses…Our system efficiently constructs a dense volumetric representation of the scene. Section 4.1; We construct a novel continuous 3D representation of a scene that maps each point and viewing direction to a color and opacity value, F0: (V(X),v) -> (c, σ),∀x ∈ V… );
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to implement Sun’s density and feature voxel grids using Clark’s B+ tree-based VDB representation. Doing so provides an efficient hierarchical structure for storing and querying volumetric voxel information (Clark Pg. 6115, Section 1; a tree-based scene representation that improves memory efficiency because information is only stored near occupied areas. The tree is very efficient to query which speeds up rendering and therefore also optimization…efficiently represent 3D scenes and can grow as more areas of the scene are explored…efficient method for optimizing volume properties…). Such modification would retain Sun’s geometry and appearance representations while predictably improving the efficiency of memory, storing, and querying the respective volumetric data structures.
Regarding claim 2, Sun in view of Clark discloses the computing device of claim 1, but Sun does not disclose wherein the model volume data structure is generated by a machine learning model.
In the same art of voxel-based volumetric scene representation for novel-view rendering, Clark discloses wherein the model volume data structure is generated by a machine learning model (Clark Pg. 6126, Section 4.1; Our representation combines a VDB tree with a neural network interpolator, which we call an nVDB tree…The function F(θ), projects the features sampled from the VDB grid to the color and opacity outputs. This projection is modelled using a shallow fully-connected neural network. Pg. 6127 and Fig. 3; During rendering the features are sampled from the volume using trilinear interpolation and a shallow MLP is used to project these features to color and occupancy values…once all the rays are rendered).
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to incorporate Clark’s neural-network based generation and interpolation of volumetric scene features into Sun’s voxel-grid representation. Machine learning techniques automate image-processing tasks, reduce manual processing, and provide more robust and efficient image reconstruction while applying a known technique in the same field of neural rendering, predictably improving the ability to model scene appearance while retaining the efficient voxel-based representation for rendering, and providing an efficient learned representation.
Regarding claim 4, Sun in view of Clark discloses the computing device of claim 1, and Sun further discloses wherein determining the set of valid points from the plurality of sample points comprises removing sample points having a density value below a predetermined threshold (Pg. 5454, Section 5.2; A query point is in the known free space if the post-activated alpha value from the optimized V(density)(c) is less than the threshold τ(c)…First, we skip sampled points that are in the known free space by checking the optimized V(density)(c)…Second, we further skip sampled points in unknown space with low activated alpha value (threshold at τ(f)) by querying V(density)(f)).
Sun and Clark are combined for the reason set forth above with respect to claim 1.
Regarding claim 5, Sun in view of Clark discloses the computing device of claim 1, and Sun further discloses wherein determining the set of valid points further comprises removing sample points in the plurality of sample points that are outside a bounding box of a spatial representation of the model volume data structure (Pg. 5453, Section 5.1; We first find a bounding box (Bbox) tightly enclosing the camera frustums of training views…Our voxel grids are aligned with the Bbox…Pg. 5454, Section 5.2; We densely query V(density)(c) to find a Bbox tightly enclosing the unknown space…For each ray, we adjust the near- and far-bound…to the two endpoings of the ray-box intersection…).
Sun and Clark are combined for the reason set forth above with respect to claim 1.
Regarding claim 6, Sun in view of Clark discloses the computing device of claim 1, and Sun further discloses wherein determining the set of valid points further comprises removing sample points along the ray after an accumulated density threshold is reached (Pg. 5451, Section 3; Eq. (2b), (2c)…where αi is the probability of termination at the point i. Pg. 5454, Section 5.2; A query point is in the known free space if the post-activated alpha value from the optimized V(density)(c) is less than the threshold τ(c)…First, we skip sampled points that are in the known free space by checking the optimized V(density)(c)…Second, we further skip sampled points in unknown space with low activated alpha value (threshold at τ(f)) by querying V(density)(f)).
Sun and Clark are combined for the reason set forth above with respect to claim 1.
Regarding claim 10, Sun in view of Clark discloses the computing device of claim 1, but Sun does not disclose wherein leaf nodes of each of the B+ tree graph correspond to voxels, and wherein the B+ tree graph is arranged based on spatial locations of the voxels.
In the same art of voxel-based volumetric scene representation for novel-view rendering, Clark discloses wherein leaf nodes of each of the B+ tree graph correspond to voxels (Clark Pg. 6126, Section 3; VDB trees also represent voxels as the leaf nodes…the structure of VDB tree makes it possibly to efficiently access voxel values), and wherein the B+ tree graph is arranged based on spatial locations of the voxels (Clark Fig. 1 and Fig. 3.; spatial features)
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to organize Sun’s volumetric voxel data using Clark’s spatially arranged VDB structure. Such hierarchical spatial organization provides efficient access to voxel values while avoiding storage of unnecessary data in unoccupied portions of the scene, yielding predictable results in improved memory and querying efficiency for Sun’s volumetric rendering system (Clark Pg. 6115, Section 1; a tree-based scene representation that improves memory efficiency because information is only stored near occupied areas. The tree is very efficient to query which speeds up rendering and therefore also optimization…efficiently represent 3D scenes and can grow as more areas of the scene are explored…efficient method for optimizing volume properties…).
Regarding claim 11, claim 11 is the method claim of system claim 1, and is accordingly rejected using substantially similar rationale as to which is set forth above with respect to claim 1.
Regarding claim 12, claim 12 has similar limitations as of claim 2, except it is the method claim, therefore, it is rejected under the same rationale as claim 2.
Regarding claim 13, claim 13 has similar limitations as of claim 4, except it is the method claim, therefore, it is rejected under the same rationale as claim 4.
Regarding claim 14, claim 14 has similar limitations as of claims 5 and 6, except it is the method claim, therefore, it is rejected under the same rationale as claim 5 and 6.
Claim(s) 9 and 15 is/are rejected under 35 U.S.C. 103 as being unpatentable over Sun et al. "Direct voxel grid optimization: Super-fast convergence for radiance fields reconstruction." In 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5449-5459. IEEE, 2022, hereinafter referred to as “Sun”, in view of Clark "Volumetric bundle adjustment for online photorealistic scene capture." In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6124-6132. 2022, and in further view of view of Lightstone et al. (US 7028022), hereinafter referred to as “Lightstone”’.
Regarding claim 9, Sun in view of Clark discloses the computing device of claim 1, but does not disclose wherein the B+ tree graph has a height of four.
In the same art of B+ trees, Lightstone discloses wherein the B+ tree graph (Column 7, lines 53-55; index 14 is stored in the form of a binary tree, such as a B- tree, B+-tree, or B*-tree) has a height of four (Column 8, lines 40-53 T4; In the table T2...T8 represent the percentile thresholds for the tree height 2 to 8).
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the B+ tree of Clark to incorporate the B+ tree graph having a height of 4 as taught by Lightstone. The motivation lies in the advantage of selecting an appropriate tree height based on memory usage and indexing efficiency. Furthermore, in accordance with MPEP 2131.03, the claimed value of “four” falls within the disclosed prior art range and therefore would have achieved results consistent with those expected from the disclosed range. Selecting a height of four from this known range would have yielded predictable results using routine optimization.
Regarding claim 15, Sun in view of Clark discloses the method of claim 11, and Clark further discloses leaf nodes of the B+ tree graph corresponds to voxels (Clark Pg. 6126, Section 3; VDB trees also represent voxels as the leaf nodes...the structure of VDB tree makes it possibly to efficiently access voxel values), and the B+ tree graph is arranged based on spatial locations of the voxels (Clark Fig. 1 and Fig. 3.; spatial features).
It would have been obvious to a person of ordinary skill in the art, before the effective filing date of the claimed invention, to organize Sun’s volumetric voxel data using Clark’s spatially arranged VDB structure. Such hierarchical spatial organization provides efficient access to voxel values while avoiding storage of unnecessary data in unoccupied portions of the scene, yielding predictable results in improved memory and querying efficiency for Sun’s volumetric rendering system (Clark Pg. 6115, Section 1; a tree-based scene representation that improves memory efficiency because information is only stored near occupied areas. The tree is very efficient to query which speeds up rendering and therefore also optimization…efficiently represent 3D scenes and can grow as more areas of the scene are explored…efficient method for optimizing volume properties…).
Sun in view of Clark does not disclose wherein the B+ tree graph has a height of four.
In the same art of B+ trees, Lightstone discloses wherein the B+ tree graph (Column 7, lines 53-55; index 14 is stored in the form of a binary tree, such as a B-tree, B+-tree, or B*-tree) has a height of four (Column 8, lines 40-53 T4; In the table T2...T8 represent the percentile thresholds for the tree height 2 to 8).
The motivation to combine would’ve been the same as that set forth in claim 9.
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 JENNY NGAN TRAN whose telephone number is (571) 272-6888. The examiner can normally be reached Mon-Thurs 8am-5pm.
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, Alicia Harrington can be reached at (571) 272-2330. 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.
/JENNY N TRAN/Examiner, Art Unit 2615
/YANNA WU/Primary Examiner, Art Unit 2615
Prosecution Insights