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 .
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)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 1, 3, 9, 10, 12, 18, and 19 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Mullia Lakshminarayana et al. (US 2025/0139878; hereinafter “Lakshminarayana”).
Regarding claim 1, Lakshminarayana discloses A method comprising: obtaining an intersection point of a ray against a primitive in a scene (“determine an intersection point (e.g., a shading point) of a primary ray traced from a virtual camera with the three-dimensional geometry,” para. 32) with a plurality of light sources (“The digital scene includes one or more digital scene elements, such as one or more digital light sources,” para. 31); applying the intersection point to a lighting neural network to obtain lighting information (“generates a property vector that includes information particular to the intersection point,” para. 33; “The trained MLP receives and evaluates the input vector to generate a shading value,” para. 35); and shading a pixel corresponding to the ray using the lighting information (“applies the shading values to the pixels to generate a photorealistic rendering,” para. 35).
Regarding claim 3, Lakshminarayana discloses wherein the lighting neural network is configured to provide a plurality of lighting results as output (“the neural module configures the compressed representation as a relightable neural asset, which is renderable under a variety of unseen illumination conditions,” para. 68).
Regarding claim 9, Lakshminarayana discloses wherein shading the pixel includes determining a reflected radiance for the pixel based on the lighting result (“the MLP is trained to … generate a radiance value, e.g., an RGB value, based on the precomputed light transport,” para. 60).
Regarding claim 10, it is rejected using the same citations and rationales described in the rejection of claim 1, with the additional limitations of A system comprising: a memory configured to store information for a lighting neural network; and a processor configured to perform operations (“memory and processor resources,” Lakshminarayana, para. 39).
Regarding claims 12 and 18, they are rejected using the same citations and rationales described in the rejections of claims 3 and 9, respectively.
Regarding claim 19, it is rejected using the same citations and rationales described in the rejection of claim 1, with the additional limitations of A non-transitory computer-readable medium storing instructions that, when executed by a processor, cause the processor to perform operations (“A non-transitory computer-readable medium storing executable instructions, which when executed by a processing device, cause the processing device to perform operations,” Lakshminarayana, published claim 18).
Claim Rejections - 35 USC § 103
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 2, 11, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Lakshminarayana in view of Müller et al. (US 2022/0284657; hereinafter “Müller”).
Regarding claim 2, Lakshminarayana does not disclose training the lighting neural network each frame.
In the same art of neural rendering, Müller teaches training the lighting neural network each frame (“When rendering dynamic content, for example changing camera position or animated geometry, the neural radiance cache needs to adapt continuously. In an embodiment, a high learning-rate is used when optimizing the neural radiance cache by gradient descent. In addition, multiple (e.g., 4) gradient descent steps may be performed per frame,” para. 54).
Before the effective filing date of the claimed invention, it would have been obvious to one having ordinary skill in the art to apply the teachings of Müller to Lakshminarayana. The motivation would have been that it “leads to even faster adaptation” (Müller, para. 54).
Regarding claims 11 and 20, they are rejected using the same citations and rationales described in the rejection of claim 2.
Claims 4-8 and 13-17 are rejected under 35 U.S.C. 103 as being unpatentable over Lakshminarayana in view of Schied et al. (US 11,436,793; hereinafter “Schied”).
Regarding claim 4, Lakshminarayana does not disclose wherein each lighting result is associated with a light source of the plurality of light sources.
In the same art of neural rendering, Schied teaches wherein each lighting result is associated with a light source of the plurality of light sources (“Lighting information used for rendering may be computed per light source … the rendering system may generate a lighting information array 310A for light source A, another array 310B for light source B … each lighting information array 310A to 310n may be processed by a light encoder … The decoder may be configured to process the encoded data in latent space and output the lighting information,” col. 10, lines 10-60; “Each of the plurality of first latent vectors in the first latent representation may encode lighting information of a single one of the plurality of light sources,” col. 7, lines 55-60).
Before the effective filing date of the claimed invention, it would have been obvious to one having ordinary skill in the art to apply the teachings of Schied to Lakshminarayana. The motivation would have been to “allow the luminance contributions of the different light sources, including the ambient light and other point light sources, to be combined accumulatively and provide scalability for the system to handle complex rendering scenarios” (Schied, col. 19, lines 40-50).
Regarding claim 5, the combination of Lakshminarayana and Schied renders obvious wherein each lighting result specifies whether an associated light source of the plurality of light sources is visible at the intersection point (“the neural module is further configured to output … a visibility term,” Lakshminarayana, para. 66).
Regarding claim 6, the combination of Lakshminarayana and Schied renders obvious wherein each lighting result specifies an intensity of an associated light source at the intersection point (“outputs the inferred or predicted result (e.g., the color values or color weights/intensities),” Schied, col. 17, lines 5-10; “the lighting information for pixel A may include the direction and intensity of light source 420A,” Schied, col. 13, lines 25-30; see claim 4 for motivation to combine).
Regarding claim 7, the combination of Lakshminarayana and Schied renders obvious wherein each lighting result specifies a reflected radiance of an associated light source at the intersection point (“the MLP is trained to … generate a radiance value, e.g., an RGB value, based on the precomputed light transport,” Lakshminarayana, para. 60; “the shading neural network may learn to directly output the color, expressed in RGB,” Schied, col. 12, lines 1-5; see claim 4 for motivation to combine).
Regarding claim 8, the combination of Lakshminarayana and Schied renders obvious wherein shading the pixel includes selecting one or more light sources of the plurality of light sources stochastically … based on the lighting result (“Based on the visibility information, the rendering system may then compute the corresponding lighting information … the subset of light sources selected for each pixel may be chosen stochastically,” Schied, col. 13, lines 15-25; see claim 4 for motivation to combine).
The combination of Lakshminarayana and Schied does not specifically recite stochastic selection with a probability density function.
The Examiner takes Official Notice that both the concepts and the advantages of using probability density functions in stochastic selection were well known and expected in the art before the effective filing date of the claimed invention, and it would have been obvious before the effective filing date of the claimed invention to apply a probability density function in the combination of Lakshminarayana and Schied in order to improve realism by allowing for more impactful light sources to be selected.
Regarding claims 13-17, they are rejected using the same citations and rationales described in the rejections of claims 4-8, respectively.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Ryan McCulley whose telephone number is (571)270-3754. The examiner can normally be reached Monday through Friday, 8:00am - 4:30pm.
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, Kee Tung can be reached at (571) 272-7794. 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.
/RYAN MCCULLEY/Primary Examiner, Art Unit 2611
Prosecution Insights