CTFR 17/141,430 CTFR 79302 DETAILED ACTION Notice of Pre-AIA or AIA Status 07-03-aia AIA 15-10-aia The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA. Applicant's amendment filed on 02/23/2026 has been entered. Claims 1-30 are pending. Claims 1, 7, 13 and 19-25 are currently amended. Information Disclosure Statement The information disclosure statement (IDS) submitted on 05/13/2026, 12/30/2025, 09/19/2025 and 09/19/2025 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner. Claim Rejections - 35 USC § 103 07-06 AIA 15-10-15 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. 07-20-aia AIA 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. 07-103 AIA The text of those sections of Title 35, U.S. Code not included in this action can be found in a prior Office action. 07-23-aia AIA 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. 07-20-02-aia AIA This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention. 07-21-aia AIA Claim s 1-2, 7-8, 13-14, 19-20, and 25-26 are rejected under 35 U.S.C. 103 as being unpatentable over Somanath et al. (Somanath), US Patent No. 10,706,890 and further in view of Agarwala et al. (Agarwala), US Patent Application Publication No. US 2007/0076016 A1 . As to independent claim 1, Somanath discloses one or more processors, comprising: circuitry to use one or more neural networks to (Abstract and col. 7, lines 50-67: synthesizing multiple images into a single image using a neural network ) : determine trajectories of a plurality of objects in an area based, at least in part, on images captured from two or more point of view (POV) viewpoints of the plurality of objects showing the area (Abstract, col. 6, lines 29-51: capture video stream (a series of images) of an object or a scene from different perspectives (viewpoints) or positions; col. 8, lines 18-23 : the input images may contain both camera and object motions, where an output image may be such that the virtual-generated camera viewpoint may be geometrically in the middle of the two input camera views presented by the two images, where the object motions are interpolated to be half-way between the two inputs); Figure 3A: the images include objects such as a woman playing with bubbles; Figures 3B: the images include objects such as a woman and a man are fighting each other); determine one or more overlapping locations of the plurality of objects based, at least in part, on the trajectories and the images (col. 12, lines 32-43: image 325 represents overlapping of images 1 321 and 2 323 ) ; and generate one or more additional images comprising the plurality of objects from a viewpoint that is different from the two or more viewpoints based, at least in part, on the one or more overlapping locations (col. 12, lines 32-43: image 327 is a final “middle” image generated through view synthesis and represents the intermediary view of images 1 321 and 2 323). Somanath discloses in Figure 6, which is a computing environment capable of supporting the operations of capturing images at multiple positions or multiple points in times, where the multiple images represent multiple views of an object or a scene, and synthesizing by a neural network the multiple images into a single image including a middle image of the multiple images and representing an intermediary view of the multiple views (Abstract, Figure 6 and col. 19, line 39 – col. 20, line 7). Somanath further discloses the Object and Velocity and Direction module 603 may be adapted to estimate the dynamics of a virtual object being moved, such as its trajectory, velocity, momentum (col. 21, line 64 – col. 22, line 9). Thus, one of ordinary skill in the art would interpret that these teaching of Somanath would imply “determine trajectories of a plurality of objects in an area based, at least in part, on images captured from two or more viewpoints of the area”. Somanath, however, does not disclose generating one or more additional images comprising the plurality of objects and additional objects from a viewpoint that is different from the two or more point of view (POV) viewpoints based, at least in part, on the one or more overlapping locations. In the same field of endeavor, Agarwala discloses providing an architecture that facilitates producing a single image that can visualize a scene too large to depict form any single perspective view, images from the scene can be stitched together to form a multi-perspective image of the entire extent of the scene depicted by the input images and the respective images overlap (Abstract). Agarwala further discloses a 3- dimensional model of the world depicted in the input images can be rendered, and this rendering can employ projection matrices that describe the camera locations and orientations based upon feature points (e.g., dominant objects) within the 3-dimensional model, which represents a multi-perspective view of the scene at a selected dominant depth, wherein the dominant depth can be based upon the dominant geometry and/or the feature points (objects) (paragraph [0014]). Agarwala further disclose in paragraph [0041] and Figure 5 that determining the location, orientation and projection matrices for each camera based upon the images 104, as well as a sparse cloud of 3-dimensional points that describe the scene geometry, such as feature points (objects or important features within the scene), wherein the path of the camera may not be a straight line, and different camera orientations between the images 104 may produce a curve. Agarwala further discloses in paragraph [0043] that if the images 104 were produced by a camera that was not pointed directly at the objects in a scene, the system then provides a means such that a user can select features (additional objects) that define the new coordinate system, rather than having it automatically defined. Agarwala further discloses projecting each pixel of an image 104 from the plurality of images 104 onto the picture surface, which can ultimately be rendered into the optimized image 108 (paragraph [0045]). It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the system of Somanath to include generating one or more additional images comprising the plurality of objects and additional objects from a viewpoint that is different from the two or more point of view (POV) viewpoints based, at least in part, on the one or more overlapping locations, as taught by Agarwala for the purpose of creating a multi-perspective image of a scene captured in the input photographs. As to dependent claim 2, Somanath discloses wherein the one or more neural networks are further to select a subset of images based, at least in part, on the one or more overlapping locations, wherein the subset of images is to be combined to generate the one or more additional images (Figures 3B-3E, 4A) . Claims 7-8, 13-14, 19-20 and 25-26 contain similar limitations of claims 1-2. Therefore, claims 7-8, 13-14, 19-20 and 25-26 are rejected under the same rationale . 07-22-aia AIA Claim s 3, 9, 15, 21 and 27 are rejected under 35 U.S.C. 103 as being unpatentable over Somanath and Agarwala as applied to claim s 1-2, 7-8, 13-14, 19-20, and 25-26 above, and further in view of Han et al. (Han), NPL “Human Body Action Identifying Method based on the 3D convolutional neural network”, Document ID: CN-105160310-A, published on 2015-12-16, pages: 7 (cited in Non-Final rejection dated 01/19/2024) . As to dependent claim 3, Somanath discloses main CNN403 and CNN405 are used to learn to map flow, motion, displacement, etc. , between any two sets of frames/patches (col. 15, lines 20-31) . Somanath, however, does not disclose wherein the one or more neural networks include a three-dimensional convolutional neural network (3D-CNN) to classify motion of the plurality of objects. In the same field of endeavor, Han discloses a 3D convolutional neural network-based human body action identifying method for solving computer vision and pattern recognition field of human action recognition problem (Abstract). Han further disclose using the 3D convolutional neural network to solve the recognition problem of human-action, and using the 3D convolutional neural network for motion recognition (page 3). Han further discloses obtaining characteristic value of picture/image to be connected one classifier, which can realize multiple classification of motion image (page 5). It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the system of Somanath to include the one or more neural networks include a three-dimensional convolutional neural network (3D-CNN) to classify motion of the plurality of objects, as taught by Han. Han suggests that using the 3D convolution neural network is for motion recognition. Claims 9, 15, 21 and 27 contain similar limitations of claim 3. Therefore, claims 9, 15, 21 and 27 are rejected under the same rationale . 07-22-aia AIA Claim s 4-6, 10-12, 16-18, 22-24 and 28-30 are rejected under 35 U.S.C. 103 as being unpatentable over Somanath and Agarwala as applied to claim s 1-2, 7-8, 13-14, 19-20, and 25-26 above, and further in view of Mezghanni et al., (Mezghanni), European Patent Application, EP 3975065 A1 . As to dependent claim 4, Somanath discloses variations in a number of filters per each layer of a neural network, a number of layers in the encoder-decoder structure of CNN 405 or main CNN 403 (col. 15, lines 32-46) , and main CNN403 and CNN405 are used to learn to map flow, motion, displacement, etc. , between any two sets of frames/patches (col. 15, lines 20-31). Somanath, however, does not disclose and wherein the one or more neural networks include one or more intersecting variational auto-encoders (VAEs) to encode features and a motion, classified by a three-dimensional convolutional neural network (3D-CNN), for the images to one or more latent spaces. In the same field of endeavor, Mezghanni discloses method for training a deep-learning generative model configured to output 3D modeled objects (Abstract). Mezghanni further discloses the training method may comprise deep-learning generative model which includes a 3D generative neural network, wherein the 3D generative neural network includes a Variational Autoencoder (VAE) or a Generative Adversarial Network (paragraph [0008]). Mezghanni further discloses the deep-learning generative model may include a Variational Auto Encoder , and/or any other Neural Network (e.g., Convolutional Neural Network), and the deep-learning generative model may generate a family of synthesized 3D objects (paragraph [0036]). Mezghanni further discloses the deep learning generative model trained according to the method may be used within a method for synthesizing 3D modeled objects, and the synthesizing may comprise obtaining a latent representation from a latent space of the trained 3D generative neural network and generating the 3D modeled object from the obtained latent representation, wherein the latent representation for generating the 3D modeled object may be obtained from any kind of sampling from the latent space (paragraph [0051]). It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the system of Somanath to include “the one or more neural networks include one or more intersecting variational auto-encoders (VAEs) to encode features and a motion, classified by a three-dimensional convolutional neural network (3D-CNN), for the images to one or more latent spaces”, as taught by Mezghanni. Mezghanni suggests that the training method leverages on improvements provided by the field of machine-learning (Mezghanni, paragraph [0017]). As to dependent claim 5, Somanath does not teach but Mezghanni discloses wherein the one or more neural networks are further to sample one or more latent spaces to determine the trajectories (Mezghanni, paragraphs [0052]-[0053]) . As to dependent claim 6, Somanath does not teach but Mezghanni discloses wherein the one or more neural networks include a two-stage generative adversarial network (GAN) to generate the additional images based at least in part upon interactions determined from the trajectories, determined by sampling one or more latent spaces using the images (Mezghanni, paragraph2 [0044]-[0050]) . Claims 10-12, 16-18, 22-24 and 28-30 contain similar limitations of claims 4-6. Therefore, claims 10-12, 16-18, 22-24 and 28-30 are rejected under the same rationale . Response to Arguments Applicant’s arguments and amendments filed on 02/23/2026 have been fully considered but they are not deemed fully persuasive. Applicant’s arguments with respect to claims 11-30 have been considered but are moot in view of the new ground(s) of rejection as explained here below, necessitated by Applicant’s substantial amendment (i.e., generating one or more additional images comprising the plurality of objects and additional objects from a viewpoint that is different from the two or more point of view (POV) viewpoints based, at least in part, on the one or more overlapping locations) to the claims which significantly affected the scope thereof. Please see the rejection above with newly cited prior art Agarwala . Conclusion 07-39 AIA THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37CFR 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 extension fee 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 CHAU T NGUYEN whose telephone number is (571)272-4092. The examiner can normally be reached on Monday-Friday from 8am to 5pm. If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Cesar Paula, can be reached at telephone number 5712724128. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300. 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) Form at https://www.uspto.gov/patents/uspto-automated-interview-request-air-form. Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). /CHAU T NGUYEN/Primary Examiner, Art Unit 2145 Application/Control Number: 17/141,430 Page 2 Art Unit: 2145 Application/Control Number: 17/141,430 Page 3 Art Unit: 2145 Application/Control Number: 17/141,430 Page 4 Art Unit: 2145 Application/Control Number: 17/141,430 Page 5 Art Unit: 2145 Application/Control Number: 17/141,430 Page 6 Art Unit: 2145 Application/Control Number: 17/141,430 Page 7 Art Unit: 2145 Application/Control Number: 17/141,430 Page 8 Art Unit: 2145 Application/Control Number: 17/141,430 Page 9 Art Unit: 2145 Application/Control Number: 17/141,430 Page 10 Art Unit: 2145
Prosecution Insights