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 Arguments/Amendments
The amendment filed 07/29/2026 in response to the Non-Final Office Action mailed on 07/16/2026 has been entered.
Claims 1-5, 7-9, and 11-22 are currently pending in U.S. Patent Application No. 18/958,415.
The Applicant’s remarks filed 07/29/2026 have been fully considered and responded to below.
The previously noted claim objections and rejections under 35 U.S.C. 112(b) are removed in view of the claim amendments.
Regarding the 35 U.S.C. 103 rejections, the Applicant’s remarks have been fully considered but are moot because the new grounds of rejection regarding the amended limitation no longer relies on the combination of references presented in the Non-Final Rejection. A change in scope necessitated by the Applicant’s amendments has led to an updated search revealing new art.
Claim Objections
Claims 14 and 16 are objected to because of the following informalities:
Claim 14 does not have the same claim amendment as the similarly amended claim 2 regarding “a 3D object generated by a second machine-learning model”. Similarly, claim 16 does not have the same claim amendment as the similarly amended claim 9. The Examiner recommends that the Applicant review these claims to ensure they are presented as intended.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claims 1-5, 7-9, and 11-22 rejected under 35 U.S.C. 102(a)(1) as being anticipated by Shen et al. (“SuperGaussian: Repurposing Video Models for 3D Super Resolution”, noted as document #45 from IDS filed 02/27/2025; hereinafter “Shen”).
Regarding Claim 1, Shen discloses a method comprising: receiving, by a processing device, a first three-dimensional (3D) representation of an object in a first resolution (Fig. 2, Shen discloses obtaining a low-resolution 3D representation.);
generating, by the processing device, a first video of the object from multiple viewpoints of the first 3D representation, the first video generated by rendering the first 3D representation from the multiple viewpoints to map the first 3D representation to an intermediate video representation of the object, each frame of the first video comprising a respective image of the object rendered from a respective viewpoint of the multiple viewpoints (Fig. 2, 3.2. Problem Formulation, Shen discloses rendering an intermediate video based on the 3D representation.);
generating, using a machine-learning model and from the first video, a second video of the object in a higher resolution than the first video (Fig. 2, 3.3. Initial Upsampling, Shen discloses using VideoGigaGAN to upsample a video.); and
outputting, by the processing device, a second 3D representation of the object in a second resolution higher than the first resolution and based on a 3D reconstruction of the object from the second video, the 3D reconstruction fitting the second 3D representation to the object as depicted in frames of the second video (Fig. 2, 3.4. 3D Optimization via Gaussian Splats, Shen discloses fitting gaussians to the upsampled videos to generate a higher resolution 3D representation.).
Claim 20 is the non-transitory computer storage medium claim corresponding to claim 1 and is similarly rejected (see Implementation details and the usage of GPUs and VRAM.).
Regarding Claim 2, Shen discloses the method of claim 1, wherein a format of the first 3D representation is one of Gaussian splats, neural radiance fields (NeRFs), a low-poly mesh, a digital video, a sensor scan of a lidar or radar system, or a 3D object generated by a second machine-learning model (4.1. Setup, Shen discloses utilizing low resolution gaussian splats as input into their disclosed model.).
Claim 14 is the non-transitory computer storage medium claim corresponding to claim 2 and is similarly rejected.
Regarding Claim 3, Shen discloses the method of claim 2, wherein the second machine-learning model is a text-to-3D generative model that generates the first 3D representation based on a text prompt (Fig. 1, Shen discloses utilizing a text-to-3D model to generate a low-resolution 3D representation.).
Regarding Claim 4, Shen discloses the method of claim 1, wherein the multiple viewpoints of the first video follow a trajectory around at least a portion of the object (Fig. 2, 3.2. Problem Formulation, Shen discloses rendering a sequence of RGB images (used to generate a video) by rendering several smooth trajectories with corresponding viewpoints.).
Regarding Claim 5, Shen discloses the method of claim 4, wherein generating the first video includes generating a plurality of videos, each video of the plurality of videos following a respective trajectory around at least a respective portion of the object (Fig. 2, 3.2. Problem Formulation, Shen discloses generating several sequences of RGB images, each corresponding to a respective smooth trajectory.).
Claim 18 is the non-transitory computer storage medium claim corresponding to claim 5 and is similarly rejected.
Regarding Claim 7, Shen discloses the method of claim 4, wherein the multiple viewpoints are sampled along the trajectory such that camera movement between adjacent frames of the first video enables the machine-learning model to leverage temporal alignment in between the adjacent frames of the first video when generating the second video (3.2. Problem Formulation, Shen discloses that camera movement between adjacent frames “is sufficiently small” to be input into a video upsampler.).
Regarding Claim 8, Shen discloses the method of claim 1, wherein the machine-learning model is a video-based generative upsampler (Fig. 2, 3.3. Initial Upsampling, Shen discloses utilizing VideoGigaGAN.).
Claim 15 is the non-transitory computer storage medium claim corresponding to claim 8 and is similarly rejected.
Regarding Claim 9, Shen discloses the method of claim 8, wherein the video-based generative upsampler is fine-tuned to reduce artifacts of a format of the first 3D representation, the video-based generative upsampler being fine-tuned using pairs of low-resolution and high-resolution videos depicting degradation specific to the format of the first 3D representation (3.3. Initial Upsampling, Shen discloses fine-tuning the video upsampler to reduce artifacts.).
Regarding Claim 11, Shen discloses the method of claim 1, wherein a format of the second 3D representation is Gaussian splats, each Gaussian splat indicating a position in space, a size value, an orientation, a color, and an opacity value (3.4. 3D Optimization via Gaussian Splats, Shen discloses fitting Gaussian splats to the output upsampled video.).
Claim 17 is the non-transitory computer storage medium claim corresponding to claim 11 and is similarly rejected.
Regarding Claim 12, Shen discloses the method of claim 11, wherein the second 3D representation is generated by fitting the Gaussian splats to the object from the second video, the fitting iteratively adjusting properties of the Gaussian splats to minimize a difference between renderings of the Gaussian splats and the frames of the second video and removing one or more temporal inconsistencies present in the second video (3.4. 3D Optimization via Gaussian Splats, Shen discloses utilizing losses L1 and LSSIM to optimize the 3D gaussian.).
Regarding Claim 13, Shen discloses a system comprising: a memory component; and one or more processing devices coupled to the memory component, the one or more processing devices to perform operations comprising (see Implementation Details, wherein Shen discloses utilizing GPUs and VRAM to train and implement their disclosed models, which are performed on a computing device.):
receive a first three-dimensional (3D) representation of an object in a first resolution (Fig. 2, Shen discloses obtaining a low-resolution 3D representation.);
generate a first video of the object from multiple viewpoints of the first 3D representation, the first video generated by rendering the first 3D representation from the multiple viewpoints to map the first 3D representation to an intermediate video representation of the object, each frame of the first video comprising a respective image of the object rendered from a respective viewpoint of the multiple viewpoints (Fig. 2, 3.2. Problem Formulation, Shen discloses rendering an intermediate video based on the 3D representation.);
generate, using a machine-learning model and from the first video, a second video of the object in a higher resolution than the first video (Fig. 2, 3.3. Initial Upsampling, Shen discloses using VideoGigaGAN to upsample a video.);
generate a second 3D representation of the object in a second resolution higher than the first resolution by fitting Gaussian splats to the object as depicted in frames of the second video; and output the second 3D representation of the object (Fig. 2, 3.4. 3D Optimization via Gaussian Splats, Shen discloses fitting gaussians to the upsampled videos to generate a higher resolution 3D representation, which are outputted for visualization.).
Regarding Claim 16, Shen discloses the system of claim 15, wherein the video-based generative upsampler is fine-tuned to reduce artifacts of a format of the first 3D representation (3.3. Initial Upsampling, Shen discloses fine-tuning the video upsampler to reduce artifacts.).
Regarding Claim 19, Shen discloses the system of claim 13, wherein the object comprises a scene including multiple items (see Fig. 10.).
Regarding Claim 21, Shen discloses the method of claim 1, wherein the 3D reconstruction fits the second 3D representation to the object using known camera poses of the multiple viewpoints from which the first 3D representation is rendered (3.4. 3D Optimization via Gaussian Splats, Shen discloses utilizing camera information for optimization.).
Regarding Claim 22, Shen discloses the method of claim 5, wherein generating the second video includes generating, using the machine-learning model, a respective upsampled video from each video of the plurality of videos, and wherein the 3D reconstruction fits the second 3D representation to the object as depicted in frames of each respective upsampled video (see Fig. 2, 3.3. Initial Upsampling, Shen discloses utilizing VideoGigaGAN to generate an upsampled video.).
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 PROMOTTO TAJRIAN ISLAM whose telephone number is (703)756-5584. The examiner can normally be reached Monday - Friday 8:30 am - 5:00 pm EST.
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, Chan Park can be reached at (571) 272-7409. 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.
/PROMOTTO TAJRIAN ISLAM/Examiner, Art Unit 2669 /CHAN S PARK/Supervisory Patent Examiner, Art Unit 2669
Prosecution Insights