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 .
Response to Amendment
In response to the amendment to independent claim 1, the rejection of claims 1-8 under 35 U.S.C. § 112(b) is withdrawn.
In response to the amendment to independent claim 1, the rejection of claims 1-8 under 35 U.S.C. § 101 is withdrawn.
In response to the amendments to independent claims 1, 9, and 13, the previously-applied rejections of these claims under 35 U.S.C. § 102(a)(1) in view of Yin is withdrawn. However, upon further consideration, a new ground of rejection is applied under 35 U.S.C. § 103, wherein the instant application is unpatentable over Yin in further view of Buchholz.
Response to Arguments
Applicant’s arguments filed 30 March 2026, taken in conjunction with Applicant’s discussion with Examiner in the interview of 20 March 2026, with respect to Examiner’s objection to the drawings have been fully considered and are persuasive. The objection to the drawings has been withdrawn. Applicant’s remarks with respect to the rejection of claims 1, 9, and 13, taken in conjunction with the amendment to claims 1, 9, and 13 and antecedent basis amendments to claims 2, 6, 10, 14, and 18 have changed the grounds of rejection for claims 1, 9, and 13 as mentioned above.
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.
Claims 1-2,4,6,8-10,12-14,16,18 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Yin et al. (US PG Pub 20220277514 A1, hereinafter “Yin”) in view of Buchholz et al. (“Fourier Image Transformer” in proceedings of the IEEE/CVF Conference of Computer Vision and Pattern Recognition (pp. 1846-1854), 2022., hereinafter “Buchholz”).
Regarding claim 1, Yin discloses a scene reconstruction apparatus and system comprising:
a processor (para. 0159, “As shown in FIG. 10, the computing device 1000 may include one or more processor(s) 1002”); and
memory storing instructions (paras. 0159-0162, with reference to memory 1004 within computing device 1000) that, when executed by the processor, cause the processor to:
generate a geometric viewing review vector using pixel coordinates and intrinsic parameters about a camera for an image captured about a scene (process summarized within paras. 0046-0047, and more specifically within paras. 0051-0058, wherein the reconstruction of the scene is reliant on the calculation of geometric viewing review vectors, in this case using a determined principal point, 2D image pixel coordinates, camera focal length, and depth map to generate a three-dimensional scene comprised of a plurality of viewing vectors originating at the principal point and scaled to represent the actual scene using the aforementioned parameters);
derive geometric embeddings from the geometric viewing vector associated with the image for the camera (paras. 0029 and 0046-0047 for a description of the derivation of depth shift, scale depth data, and a depth map from camera image data and intrinsic parameters from the camera for the determination of the geometric embeddings, where these statistics are all potential embodiments of geometric embeddings);
compute a representation by augmenting image embeddings with the geometric embeddings, the image embeddings associated with visual characteristics about the image (paras. 0046-0047 and 0051-0054, utilizing geometric embeddings such as intrinsic parameters and depth shifts to correct for unscaled depth calculations and image reconstruction values); and
estimate a scaled depth of the image from the representation (para. 0057, wherein the depth data and geometric embeddings are used to augment a raw/uncorrected depth map to a corrected, scaled version).
Specifically, Yin discloses a 3D scene recovery and reconstruction method and system, operating by training a 3D point cloud model to recover camera parameters from image depth maps and unprojecting 2D image data into a 3D image space using the collected data and parameters.
Yin does not disclose encoding the geometric viewing vector using Fourier encoding associated with the scene, or where the derived geometric embeddings have dimensions associated with frequency bands identified by the Fourier encoding at a pixel level.
However, Buchholz discloses encoding the geometric viewing vector using Fourier encoding associated with the scene (pgs. 1848-1849, section 3, subsection 3.1 “Fourier Domain Encodings”, wherein Buchholz discloses a method of encoding image data within the Fourier domain), and where the derived geometric embeddings have dimensions associated with frequency bands identified by the Fourier encoding at a pixel level (pg. 1846 fig. 1 and description, and pgs. 1849-1850, section 3.4 for the disclosure of pixel-level Fourier encoding, wherein the frequency band identification and dependency is disclosed as low-frequencies are used to identify overall frequency patterns and higher frequencies).
Specifically, Buchholz discloses a Fourier image transformer which employs a transformer architecture to encode image data within the frequency domain to perform image analysis tasks. Buchholz’s image encoding method uses computed tomography images for validation, but emphasizes the wide-ranging applicability of the encoding, including in super-resolution approaches.
Thus, it would have been obvious to the ordinarily skilled artisan prior to the effective filing date of the claimed invention to have utilized the Fourier encoding method of Buchholz within the method and system of Yin as the application of a known method to a known device, yielding the predictable improvement of enabling frequency-based geometric embedding analysis of images, and identification and encoding of frequency-aware pixel-level information.
Claims 9 and 13 are rejected, mutatis mutandis, for reasons similar to claim 1.
Regarding claims 2, 10, and 14, Yin in view of Buchholz discloses all limitations of claims 1, 9, and 13, respectively. Yin further discloses wherein the instructions to derive the geometric embeddings further include instructions to:
normalize the geometric viewing vector by unprojecting the pixel coordinates into a three- dimensional (3D) space for a pixel and factoring the intrinsic parameters (paras. 0049-0050 and 0055-0057, describing the unprojecting of the 2D image into the 3D space using pixel coordinates and intrinsic camera parameters). Yin also discloses wherein encoding of the disclosed viewing vector is done independently of the scene-associated pose (para. 0052, wherein, although the encoding of the extrinsic camera parameters such as pose is mentioned as a potential embodiment, the implementation and best-means for the disclosed invention exclusively utilize the camera’s intrinsic parameters), and wherein the encoding factors a camera center and the identification of dimensions of geometric objects within the camera frame (paras. 0051-0056 for the principal point, which is the center of the camera; and para. 0046 for the identifications of the dimensions of geometric objects within the camera frame).
Yin does not disclose encoding the geometric viewing vector using the Fourier encoding independent of pose associated with the scene, or where the derived geometric embeddings have dimensions associated with the frequency bands identified by the Fourier encoding at a pixel level.
However, Buchholz discloses encoding the geometric viewing vector using the pose-independent Fourier encoding associated with the scene, (pgs. 1848-1849, section 3, subsection 3.1 “Fourier Domain Encodings”, wherein Buchholz discloses a method of encoding image data within the Fourier domain), and where the derived geometric embeddings have dimensions associated with the frequency bands identified by the Fourier encoding at a pixel level (pg. 1846 fig. 1 and description, and pgs. 1849-1850, section 3.4 for the disclosure of pixel-level Fourier encoding, wherein the frequency band identification and dependency is disclosed as low-frequencies are used to identify overall frequency patterns and higher frequencies). Thus, it would have been obvious to one having ordinary skill in the art prior to the effective filing date of the claimed invention to have incorporated this aspect of the disclosure of Buchholz within the method and system of Yin in view of Buchholz according to the rationale of claim 1.
Regarding claims 4, 12, and 16, Yin in view of Buchholz discloses all limitations of claims 2, 10, and 14, respectively. Yin further discloses wherein the instructions further include instructions to predict[,] by a learning model[,] feature positions about objects within the scene using scale priors derived from the geometric viewing vector (paras. 0046-0054 and 0067-0076, wherein the predictions of feature positions about objects within scenes using scale priors are, under Examiner’s broadest reasonable interpretation, the use of incrementally updated depth maps using encoded intrinsic camera parameters; a point cloud model is used to predict depth adjustment for accurate scene reconstruction), and the scale priors were unknown during training of the learning model that processed known priors representing appearance characteristics about the objects without depth information (para. 0002, specifically directed to the unknown initial depth information and unknown scale priors).
Regarding claims 6 and 18, Yin in view of Buchholz discloses all limitations of claims 2 and 14, respectively. Yin further discloses wherein the instructions further include instructions to encode the geometric viewing vector using the Fourier encoding (disclosed by Buchholz, with the combination rationale of claim 1) such that an origin of a coordinate system for the camera is a reference point for the image embeddings (para. 0051-0053, wherein the origin of the coordinate system is the principal point, embedded as a camera parameter).
Allowable Subject Matter
Claims 3, 5, 7, 11, 15, 17, and 19 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Conclusion
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 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 ROHAN TEJAS MUKUNDHAN whose telephone number is (571)272-2368. The examiner can normally be reached Monday - Friday 9AM - 6PM.
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, Gregory Morse can be reached at 5712723838. 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.
/ROHAN TEJAS MUKUNDHAN/Examiner, Art Unit 2663
/GREGORY A MORSE/Supervisory Patent Examiner, Art Unit 2698
Prosecution Insights