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 .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 6/26/2026 has been entered.
Response to Arguments
Applicant’s arguments with respect to the claim(s) 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.
DETAILED ACTION
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claim 13 rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
For dependent claim 13, parent claim 11 establishes a “text-to-image diffusion model” and a “text-to-video diffusion model”. Claim 13 goes on to recite the phrase “the diffusion model” and it is unclear and ambiguous to which of the previously established “text-to-image diffusion model” and “text-to-video diffusion model” is being referenced by the phrase “the diffusion model.
Appropriate correction is required.
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.
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.
Claim(s) 1, 2, 6-12, 16, 18 and 19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Zhao et al., Animate 124: Animating One Image to 4D Dynamic Scene, arXiv, November 2023 (hereinafter “Zhao”) in view of Alesiani et al. (U.S. Patent Application Publication 2024/0296919 A1, hereinafter “Alesiani”) and Li et al., VideoGen: A Reference-Guided Latent Diffusion Approach for High Definition Text-to-Video Generation, arXiv, September 2023 (hereinafter “Li”).
For claim 1, Zhao discloses a framework (page 1) to: receive an input comprising at least one of text or natural language data, the input indicating one or more features of content, the content comprising at least one of an object or a scene (disclosing acquisition of an input image and a text prompt to indicate features of content comprising an object and a scene (pages 1-2/Fig. 1)); initialize a content model, according to the input, to represent the content in three spatial dimensions and a time dimension (disclosing initialization of a dynamic neural radiance field (NeRF) model as a content model according to the input to represent the content in three spatial dimensions and a time dimension (pages 1-2/Fig. 1; page 4/Fig. 2)); update the content model by rendering one or more sequences of frames from the content model using a text-to-image diffusion model and a text-to-video diffusion model (disclosing the dynamic NeRF model is dynamic to be updated by rendering frames from the dynamic NeRF model using latent diffusion models including a text-to-image diffusion model and a text-to-video diffusion model (pages 4-5 and 7)); and cause at least one of (i) a simulation to be performed using the content model or (ii) presentation of the content model using a display (disclosing the updated dynamic NeRF model is presented for display (page 9/Fig. 6; and page 11/Fig. 8)).
Zhao does not disclose a processor comprising one or more circuits to determine, using a latent diffusion model, at least one metric of one or more sequences of frames, and modifying the content model according to the at least one metric, until a convergence condition is satisfied.
However, these limitations are well-known in the art as disclosed in Alesiani.
Alesiani similarly discloses a system and method for implementing a sequential diffusion model as a content model to update the sequential diffusion model to implement a latent diffusion model for image synthesis to perform a simulation (par. 5, 37, 61 and 138). Alesiani explains its system is implement with a processor comprising circuitry (par. 142). Alesiani further explains the system determines, using the latent diffusion model, an equation as a metric of a sequence of frames and modifies the sequential diffusion model according to the metric to satisfy a convergence condition (par. 62, 78 and 117). It follows Zhao may be accordingly modified with the teachings of Alesiani to implement its framework with a processor and circuitry to determine, using its late diffusion model, a metric of its one or more sequences and to modify its content model according to its metric until a convergence condition is satisfied.
A person having ordinary skill in the art (PHOSITA) before the effective filing date of the claimed invention would find it obvious to modify Zhao with the teachings of Alesiani. Alesiani is analogous art in dealing with a system and method for implementing a sequential diffusion model as a content model to update the sequential diffusion model to implement a latent diffusion model for image synthesis to perform a simulation (par. 5, 37, 61 and 138). Alesiani discloses its use of a convergence condition is advantageous in appropriately conditioning a diffusion generation process to synthesize video (par. 62, 78 and 117). Consequently, a PHOSITA would incorporate the teachings of Alesiani into Zhao for appropriately conditioning a diffusion generation process to synthesize video.
Zhao as modified by Alesiani does not disclose providing an input to each of a text-to-image diffusion model and a text-to-video diffusion model.
However, these limitations are well-known in the art as disclosed in Li.
Li similarly discloses a system and method for generating content such as video using latent diffusion (page 1). Li explains its system may be implemented with a text-to-image diffusion model and a reference-guided text-to-video diffusion model where text as input is provided to each of the text-to-image diffusion model and the reference-guided text-to-video diffusion model (pages 3-4/Fig. 2). It follows Zhao and Alesiani may be accordingly modified with the teachings of Li to provide its input to each of a text-to-image diffusion model and a text-to-video diffusion model.
A PHOSITA before the effective filing date of the claimed invention would find it obvious to modify Zhao and Alesiani with the teachings of Li. Li is analogous art in dealing with a system and method for generating content such as video using latent diffusion (page 1). Li discloses its use of input provided to each of a text-to-image diffusion model and a text-to-video diffusion model is advantageous in improving visual fidelity of content generated through latent diffusion (pages 1 and 3-4/Fig. 2). Consequently, a PHOSITA would incorporate the teachings of Li into Zhao and Alesiani for improving visual fidelity of content generated through latent diffusion. Therefore, claim 1 is rendered obvious to a PHOSITA before the effective filing date of the claimed invention.
For claim 2, depending on claim 1, Zhao as modified by Alesiani and Li discloses wherein the text-to-video diffusion model comprises a latent diffusion model that comprises one or more layers configured for the time dimension, and comprises or is coupled with an optimizer to determine the at least one metric based at least on a gradient associated with a given frame of the one or more sequences of frames (Zhao discloses its text-to-video diffusion model comprises a latent video diffusion model that includes layers of multilayer perceptrons configured for the time dimension and further includes an optimization stage as an optimizer (pages 2, 4, and 6-7); Alesiani similarly discloses a system and method for implementing a sequential diffusion model as a content model to update the sequential diffusion model to implement a latent diffusion model for image synthesis to perform a simulation (par. 5, 37, 61 and 138); Alesiani explains the system determines, using the latent diffusion model, an equation as a metric of a sequence of frames and modifies the sequential diffusion model according to the metric to satisfy a convergence condition (par. 62, 78 and 117); Alesiani further explains its system performs optimization to determine its metric based on a gradient associated with a frame of the sequence of frames (par. 39, 85, 91 and 117); and it follows Zhao may be accordingly modified with the teachings of Alesiani to implement its framework with a processor and circuitry to determine, using its late diffusion model, a metric of its one or more sequences and to modify its content model according to its metric until a convergence condition is satisfied).
For claim 6, depending on claim 1, Zhao as modified by Alesiani and Li discloses wherein the one or more circuits are to: render, from the content model, a first frame for a first time point and a second frame for a second time point subsequent to the first time point (Zhao discloses rendering, from the dynamic NeRF model, a first frame for a first timestep and a second frame for a second timestep subsequent to the first timestep (page 4; page 9/Fig. 6; and page 11/Fig. 8)); modify the content model according to the second frame (Zhao discloses the dynamic NeRF model is modified based on the second frame (page 4; page 9/Fig. 6; and page 11/Fig. 8)); and render, from the content model, a third frame for a third time point subsequent to the second time point according to the second frame (Zhao discloses rendering, from the dynamic NeRF model, a third frame for a third timestep subsequent to the second timestep based on the second frame (page 4; page 9/Fig. 6; and page 11/Fig. 8)).
For claim 7, depending on claim 1, Zhao as modified by Alesiani and Li discloses wherein the input comprises one or more images, and the one or more circuits are to update the content model according to the one or more images (Zhao discloses the input includes the text prompt as natural language data and an input image for updating the dynamic NeRF model according to the input image (pages 1-2/Fig. 1; page 4; page 9/Fig. 6; and page 11/Fig. 8); Alesiani similarly discloses a system and method for implementing a sequential diffusion model as a content model to update the sequential diffusion model to implement a latent diffusion model for image synthesis to perform a simulation (par. 5, 37, 61 and 138); Alesiani explains its system is implement with a processor comprising circuitry (par. 142); and it follows Zhao may be accordingly modified with the teachings of Alesiani to implement its framework with a processor and circuitry to update its content model according to its one or more images).
For claim 8, depending on claim 1, Zhao as modified by Alesiani and Li discloses wherein the one or more circuits are to update the content model according to a physics model to measure a physics-based realism of motion represented in the one or more sequences of frames (Alesiani similarly discloses a system and method for implementing a sequential diffusion model as a content model to update the sequential diffusion model to implement a latent diffusion model for image synthesis to perform a simulation (par. 5, 37, 61 and 138); Alesiani explains its system implements a physics-informed neural network as a physics model to determine physical loss with respect to physical law to measure physics-based realism of motion in frames (par. 49, 110 and 126); and it follows Zhao may be accordingly modified with the teachings of Alesiani to update its content model according to a physical model to measure a physics-based realism of motion in its one or more sequence of frames for realistic display of its frames).
For claim 9, depending on claim 1, Zhao as modified by Alesiani and Li discloses wherein the one or more circuits are to identify, from the content model, at least one of a joint of the object represented by the content model, a movement property of the object, or a deformation property of the object (Zhao discloses identifying, from the dynamic NeRF model, motion as a movement property of the object (page 4; page 9/Fig. 6; and page 11/Fig. 8); Alesiani similarly discloses a system and method for implementing a sequential diffusion model as a content model to update the sequential diffusion model to implement a latent diffusion model for image synthesis to perform a simulation (par. 5, 37, 61 and 138); Alesiani likewise explains its system identifies physical movements as a movement property of an object to be simulated by its sequential diffusion model (par. 49); and it follows Zhao may be accordingly modified with the teachings of Alesiani to identify a movement property of its object to appropriately display its object with the movement property).
For claim 10, depending on claim 1, Zhao as modified by Alesiani and Li discloses wherein the processor is comprised in at least one of: a system for generating synthetic data; a system for performing simulation operations; a system for performing conversational artificial intelligence (AI) operations; a system for performing collaborative content creation for three-dimensional (3D) assets; a system comprising one or more large language models (LLMs); a system for performing digital twin operations; a system for performing light transport simulation; a system for performing deep learning operations; a system implemented using an edge device; a system implemented using a robot; a control system for an autonomous or semi-autonomous machine; a perception system for an autonomous or semi-autonomous machine; 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 (Alesiani similarly discloses a system and method for implementing a sequential diffusion model as a content model to update the sequential diffusion model to implement a latent diffusion model for image synthesis to perform a simulation (par. 5, 37, 61 and 138); and it follows Zhao may be accordingly modified with the teachings of Alesiani to implement its framework in a simulation system to present a simulation of its object for display).
For claim 11, Zhao as modified by Alesiani and Li discloses a system comprising: memory for storing instructions; and one or more processing units to execute the instructions (Alesiani similarly discloses a system and method for implementing a sequential diffusion model as a content model to update the sequential diffusion model to implement a latent diffusion model for image synthesis to perform a simulation (par. 5, 37, 61 and 138); Alesiani explains its system is implement with a processor comprising circuitry for executing instructions stored in memory (par. 142-146); and it follows Zhao may be accordingly modified with the teachings of Alesiani to implement its framework with a processor and circuitry to appropriately carry out the functions of its framework) to execute operations as the processor of claim 1 (see above as to claim 1).
For claim 12, depending on claim 11, this claim is a combination of the limitations of claim 11 and claim 2. It follows claim 12 is rejected for the same reasons discussed above as to claim 11 and claim 2.
For claim 16, depending on claim 11, this claim is a combination of the limitations of claim 11 and claim 6. It follows claim 16 is rejected for the same reasons discussed above as to claim 11 and claim 6.
For claim 18, depending on claim 11, this claim is a combination of the limitations of claim 11 and claim 10. It follows claim 18 is rejected for the same reasons discussed above as to claim 11 and claim 10.
For claim 19, Zhao as modified by Alesiani and Li discloses a method (Zhao discloses a method (page 1)), comprising: receiving, by one or more processors, an input comprising at least one of text or natural language data, the input indicative of at least one of an object or a scene (Zhao discloses acquisition of an input image and a text prompt to indicate features of content comprising an object and a scene (pages 1-2/Fig. 1); Alesiani similarly discloses a system and method for implementing a sequential diffusion model as a content model to update the sequential diffusion model to implement a latent diffusion model for image synthesis to perform a simulation (par. 5, 37, 61 and 138); Alesiani explains its system is implement with a processor comprising circuitry (par. 142); and it follows Zhao may be accordingly modified with the teachings of Alesiani to implement its method with a processor and circuitry to appropriately carry out the functions of its method); initializing, by the one or more processors, based at least on the input, a plurality of spatial dimensions of a content model of the at least one of the object or the scene (Zhao discloses initialization of a dynamic neural radiance field (NeRF) model as a content model according to the input to represent the input in three spatial dimensions and a time dimension (pages 1-2/Fig. 1; page 4/Fig. 2)); updating, by the one or more processors, the content model to have a temporal dimension responsive to evaluating a plurality of frames rendered from the content model at a plurality of points in time based at least on providing the input to each of a latent text-to-image diffusion model and a latent text-to-video diffusion model having one or more temporal layers (Zhao discloses the dynamic NeRF model is dynamic to be updated over time as a temporal dimension responsive to evaluating frames rendered from the dynamic NeRF model over timestamps using a latent diffusion models including a latent text-to-image diffusion model and a latent text-to-video diffusion model having layers of multilayer perceptrons to update the dynamic NeRF model (pages 4-5 and 7; page 9/Fig. 6; and page 11/Fig. 8); Li similarly discloses a system and method for generating content such as video using latent diffusion (page 1); Li explains its system may be implemented with a text-to-image diffusion model and a reference-guided text-to-video diffusion model where text as input is provided to each of the text-to-image diffusion model and the reference-guided text-to-video diffusion model (pages 3-4/Fig. 2); and it follows Zhao and Alesiani may be accordingly modified with the teachings of Li to provide its input to each of a text-to-image diffusion model and a text-to-video diffusion model); and outputting, by the one or more processors, one or more frames from the content model (Zhao discloses the display for frames from the updated dynamic NeRF model for output (page 9/Fig. 6; and page 11/Fig. 8)).
Claim(s) 5 and 15 is/are rejected under 35 U.S.C. 103 as being unpatentable over Zhao in view of Alesiani and Li further in view of Martin Brualla et al. (U.S. Patent Application Publication 2024/0005590 A1, hereinafter “Brualla”).
For claim 5, depending on claim 1, Zhao as modified by Alesiani and Li discloses wherein the content model comprises: at least one of a Gaussian splatting representation, a neural radiance field (NeRF), a mesh representation, or a point cloud (Zhao discloses its content model as the dynamic NeRF model (pages 1-2/Fig. 1; page 4/Fig. 2)).
Zhao as modified by Alesiani and Li does not specifically disclose a deformation field to represent motion in one or more sequences of frames.
However, these limitations are well-known in the art as disclosed in Brualla.
Brualla similarly discloses a system and method for performing image synthesis using neural radiance fields (par. 2). Brualla explains its system implements a deformation field to represent movements as motion in frames for synthesizing images with a NeRF (par. 67-70). It follows Zhao, Alesiani and Li may be accordingly modified with the teachings of Brualla to implement a deformation field to represent motion in its one or more sequence of frames.
A PHOSITA before the effective filing date of the claimed invention would find it obvious to modify Zhao, Alesiani and Li with the teachings of Brualla. Brualla is analogous art in dealing with a system and method for performing image synthesis using neural radiance fields (par. 2). Brualla discloses its use of a deformation field is advantageous in representing movements in frames to facilitate appropriate image synthesis with neural radiance fields (par. 67-70). Consequently, a PHOSITA would incorporate the teachings of Brualla into Zhao, Alesiani and Li for representing movements in frames to facilitate appropriate image synthesis with neural radiance fields. Therefore, claim 5 is rendered obvious to a PHOSITA before the effective filing date of the claimed invention.
For claim 15, depending on claim 11, this claim is a combination of the limitations of claim 11 and claim 5. It follows claim 15 is rejected for the same reasons discussed above as to claim 11 and claim 5.
Claim(s) 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Zhao in view of Alesiani and Li further in view of Alimo et al. (U.S. Patent Application Publication 2024/0135623 A1, hereinafter “Alimo”).
For claim 20, depending on claim 19, Zhao as modified by Alesiani and Li discloses wherein the content model comprises a multilayer perceptron (MLP) corresponding to the temporal dimension (Zhao discloses its dynamic NeRF model includes layers of multilayer perceptrons corresponding to the time dimension (pages 2, 4, and 6)).
Zhao as modified by Alesiani and Li does not specifically disclose a three-dimensional (3D) Gaussian splatting representation.
However, these limitations are well-known in the art as disclosed in Alimo.
Alimo similarly discloses a system and method for rendering and synthesizing images with neural radiance fields (par. 2 and 53-54). Alimo explains it is known to use a 3D Gaussian splatting in place of NeRF to perform 3D reconstruction and novel view synthesis (par. 54). It follows Zhao, Alesiani and Li may be accordingly modified with the teachings of Alimo to implement a 3D Gaussian splatting representation corresponding to its spatial dimensions in its content model and coupled with a multilayer perceptron corresponding to its temporal dimension.
A PHOSITA before the effective filing date of the claimed invention would find it obvious to modify Zhao, Alesiani and Li with the teachings of Alimo. Alimo is analogous art in dealing with a system and method for rendering and synthesizing images with neural radiance fields (par. 2 and 53-54). Alimo discloses its use of a 3D Gaussian splatting representation is advantageous in appropriately facilitating 3D reconstruction and novel view synthesis for image synthesis (par. 2 and 53-54). Consequently, a PHOSITA would incorporate the teachings of Brualla into Zhao, Alesiani and Li for appropriately facilitating 3D reconstruction and novel view synthesis for image synthesis. Therefore, claim 20 is rendered obvious to a PHOSITA before the effective filing date of the claimed invention.
Claim(s) 21 is/are rejected under 35 U.S.C. 103 as being unpatentable over Zhao in view of Alesiani and Li further in view of Geng et al. (CN 116310219 A, hereinafter “Geng”) (citations are made with respect to the corresponding English translation enclosed with this Office Action).
For claim 21, depending on claim 1, Zhao as modified by Alesiani and Li does not disclose wherein a diffusion model is conditioned on at least one of a camera pose or a camera movement.
However, these limitations are well-known in the art as disclosed in Geng.
Geng similarly discloses a system and method for generating 3D content based on a condition diffusion model (pages 1-2). Geng explains its condition diffusion model may be conditioned on a camera parameter such as a camera viewing angle as camera pose for generating its 3D content (pages 4, 6, 10 and 11). It follows Zhao, Alesiani and Li may be accordingly modified with the teachings of Geng to condition its text-to-video diffusion model on a camera pose.
A PHOSITA before the effective filing date of the claimed invention would find it obvious to modify Zhao, Alesiani and Li with the teachings of Geng. Geng is analogous art in dealing with a system and method for generating 3D content based on a condition diffusion model (pages 1-2). Geng discloses its use of a camera pose advantageous in conditioning a diffusion model to appropriately reconstruct and generate 3D content (pages 4, 6, 10 and 11). Consequently, a PHOSITA would incorporate the teachings of Geng into Zhao, Alesiani and Li for conditioning a diffusion model to appropriately reconstruct and generate 3D content. Therefore, claim 21 is rendered obvious to a PHOSITA before the effective filing date of the claimed invention.
Allowable Subject Matter
Claims 3, 4, 14 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.
Claim 13 would be allowable if rewritten to overcome the rejection(s) under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), 2nd paragraph, set forth in this Office action and to include all of the limitations of the base claim and any intervening claims.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to CHARLES TSENG whose telephone number is (571)270-3857. The examiner can normally be reached 8-5.
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, Xiao Wu can be reached at (571) 272-7761. 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.
/CHARLES TSENG/ Primary Examiner, Art Unit 2613
Prosecution Insights