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 § 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 1 – 9, 13, 15, 18, 20 – 23 and 25 – 28 are rejected under 35 U.S.C. 103 as being unpatentable over Isik et al. (US Pub. No. 2022/0148135 A1) in view of Skibak et al. (US Pub. No. 2007/0109320 A1).
As to claim 1, Isik shows a computer-implemented (Fig. 1 and para. 41) method for parametric integration (Figs. 3A – 3C and paras. 54, 56 and 67 – 69), comprising: approximating a parametric integral of the at least one function (Figs. 3A – 3C and paras. 54, 56 and 67 – 69) by a machine learned function (Fig. 4 and paras. 68, 81, 94 and 98), wherein the machine learned function is trained to approximate the parametric integral (Figs. 3A – 3C and 4 and paras. 67 – 69); and synthesizing the content based on the parametric integral (Figs. 3A – 3C and 4 and paras. 66 – 69).
Isik does not show projecting at least one function to be integrated for synthesizing content onto at least one linear vector space spanned by components of a vector of functions.
Skibak shows projecting at least one function to be integrated for synthesizing content onto at least one linear vector space spanned by components of a vector of functions (Figs. 3A, 3B and 4 and paras. 85 and 86).
It would have been obvious to one of ordinary skill in the art at the time of filing to modify the teachings of Isik with those of Skibak because designing he system in this way allows the device to determine a an appropriate color of a particular pixel (para. 78).
As to claim 2, Skibak shows that one component of the vector of functions spanning the linear vector space is constant one (Figs. 3A, 3B and 4 and paras. 85 and 86).
It would have been obvious to one of ordinary skill in the art at the time of filing to modify the teachings of Isik with those of Skibak because designing he system in this way allows the device to determine a an appropriate color of a particular pixel (para. 78).
As to claim 3, Isik shows that the machine learned function is a neural network (Fig. 4 and paras. 97 and 98).
As to claim 4, Skibak shows that the projection is evaluated by at least one of Monte Carlo integration, quasi-Monte Carlo integration, and randomized quasi-Monte Carlo integration (para. 80).
It would have been obvious to one of ordinary skill in the art at the time of filing to modify the teachings of Isik with those of Skibak because designing he system in this way allows the device to determine a an appropriate color of a particular pixel (para. 78).
As to claim 5, Skibak shows that samples of the evaluation of the projection are accumulated in a multiresolution hash grid (Figs. 3A, 3B and 4 and paras. 85 and 86).
It would have been obvious to one of ordinary skill in the art at the time of filing to modify the teachings of Isik with those of Skibak because designing he system in this way allows the device to determine a an appropriate color of a particular pixel (para. 78).
As to claim 6, Skibak shows that noise in the evaluation of the projection is filtered across a domain of the parametric integral (para. 244).
It would have been obvious to one of ordinary skill in the art at the time of filing to modify the teachings of Isik with those of Skibak because designing he system in this way allows the device to diminish the influence of additional energy resulting from the spectral replicas as good as possible (para. 244).
As to claim 7, Isik shows that the domain of the parametric integral is subsampled and upscaled for parametric integration (para. 85).
As to claim 8, Isik shows that the noise is filtered by an additional machine learned function 411 (Fig. 4 and para. 110).
As to claim 9, Isik shows that the additional machine learned function is neural network (Fig. 4 and para. 110).
As to claim 13, Isik shows that the machine learned function consumes additional parameters 418 provided by at least one additional function dependent on a parameter of the parametric integral (Fig. 4 and para. 103).
As to claim 15, Isik shows that the parametric integral represents an image of a 3D scene 300 (Figs. 3A – 3C and paras. 54 and 85) and the parametric integral solves light transport simulation for the 3D scene (para. 2).
As to claim 18, Isik shows that sampling is performed by at least one of rasterization, ray tracing, and a combination of rasterization and ray tracing (para. 66).
As to claim 20, Isik shows that at least one of the steps of projecting, approximating, and synthesizing is performed on a server or in a data center to generate the content and the content is streamed to a user device (paras. 42 and 52).
As to claim 21, Isik shows that at least one of the steps of projecting, approximating, and synthesizing is performed within a cloud computing environment (paras. 42 and 52).
As to claim 22, Isik shows that at least one of the steps of projecting, approximating, and synthesizing is performed for training, testing, or certifying a neural network for creating movies, games, or images for display or employed in a headset, machine, robot, or autonomous vehicle (paras. 42 and 52).
As to claim 23, Isik shows that at least one of the steps of projecting, approximating, and synthesizing is performed on a virtual machine comprising a portion of a graphics processing unit (paras. 44 and 50).
As to claim 25, Isik shows a computer-implemented system (Fig. 1 and para. 41) for parametric integration (Figs. 3A – 3C and paras. 54, 56 and 67 – 69), comprising: a memory 134 that stores content (Fig. 1 and para. 43); and a processor 132 that is connected to the memory (Fig. 1 and para. 43) and configured to: approximate a parametric integral of the at least one function (Figs. 3A – 3C and paras. 54, 56 and 67 – 69) by a machine learned function (Fig. 4 and paras. 68, 81, 94 and 98), wherein the machine learned function is trained to approximate the parametric integral (Figs. 3A – 3C and 4 and paras. 67 – 69); and synthesize the content based on the parametric integral (Figs. 3A – 3C and 4 and paras. 66 – 69).
Isik does not show projecting at least one function to be integrated for synthesizing content onto at least one linear vector space spanned by components of a vector of functions.
Skibak shows projecting at least one function to be integrated for synthesizing content onto at least one linear vector space spanned by components of a vector of functions (Figs. 3A, 3B and 4 and paras. 85 and 86).
It would have been obvious to one of ordinary skill in the art at the time of filing to modify the teachings of Isik with those of Skibak because designing he system in this way allows the device to determine a an appropriate color of a particular pixel (para. 78).
As to claim 26, Isik shows that noise in the evaluation of the projection is filtered by an additional machine learned function 411 (Fig. 4 and para. 110).
Skibak shows that the projection is evaluated by at least one of Monte Carlo integration, quasi-Monte Carlo integration, and randomized quasi-Monte Carlo integration (para. 80).
It would have been obvious to one of ordinary skill in the art at the time of filing to modify the teachings of Isik with those of Skibak because designing he system in this way allows the device to determine a an appropriate color of a particular pixel (para. 78).
As to claim 27, Isik shows a non-transitory computer-readable media storing computer instructions (Fig. 1 and para. 41) that, when executed by one or more processors, cause the one or more processors to perform steps for parametric integration (Figs. 3A – 3C and paras. 54, 56 and 67 – 69), comprising: a memory 134 that stores content (Fig. 1 and para. 43); and a processor 132 that is connected to the memory (Fig. 1 and para. 43) and configured to: approximate a parametric integral of the at least one function (Figs. 3A – 3C and paras. 54, 56 and 67 – 69) by a machine learned function (Fig. 4 and paras. 68, 81, 94 and 98), wherein the machine learned function is trained to approximate the parametric integral (Figs. 3A – 3C and 4 and paras. 67 – 69); and synthesize the content based on the parametric integral (Figs. 3A – 3C and 4 and paras. 66 – 69).
Isik does not show projecting at least one function to be integrated for synthesizing content onto at least one linear vector space spanned by components of a vector of functions.
Skibak shows projecting at least one function to be integrated for synthesizing content onto at least one linear vector space spanned by components of a vector of functions (Figs. 3A, 3B and 4 and paras. 85 and 86).
It would have been obvious to one of ordinary skill in the art at the time of filing to modify the teachings of Isik with those of Skibak because designing he system in this way allows the device to determine a an appropriate color of a particular pixel (para. 78).
As to claim 28, Isik shows that noise in the evaluation of the projection is filtered by an additional machine learned function 411 (Fig. 4 and para. 110).
Skibak shows that the projection is evaluated by at least one of Monte Carlo integration, quasi-Monte Carlo integration, and randomized quasi-Monte Carlo integration (para. 80).
It would have been obvious to one of ordinary skill in the art at the time of filing to modify the teachings of Isik with those of Skibak because designing he system in this way allows the device to determine a an appropriate color of a particular pixel (para. 78).
Allowable Subject Matter
Claims 10 – 12, 14, 16, 17, 18 and 24 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.
Specifically, claim 10 recites that “... the additional machine learned function to filter noise uses at least one of a Noise2Noise loss and a consistency loss.”
The prior art does not show this configuration; therefore this claim contains allowable subject matter.
Also, claim 11 recites that “… the machine learned function is trained to approximate the parametric integral and then used to train the additional machine learned function for filtering the noise.”
The prior art does not show this configuration; therefore this claim contains allowable subject matter.
Also, claim 12 recites that “… the additional machine learned function for filtering the noise and the machine learned function to approximate the parametric integral are trained independently.”
The prior art does not show this configuration; therefore this claim contains allowable subject matter.
Also, claim 14 recites that “… the projection onto the constant one component is used for normalization separately for each component of the at least one function to be integrated.”
The prior art does not show this configuration; therefore this claim contains allowable subject matter.
Also, claim 16 recites that “… local exposure is approximated using a filtered version of the image.”
The prior art does not show this configuration; therefore this claim contains allowable subject matter.
Also, claim 17 recites that “… the machine learned function to approximate the at least one parametric integral is trained using randomly sampled parameters and without actual scene geometry.”
The prior art does not show this configuration; therefore this claim contains allowable subject matter.
Also, claim 19 recites that “… temporal anti-aliasing is applied across a sequence of images including the image in time.”
The prior art does not show this configuration; therefore this claim contains allowable subject matter.
Also, claim 24 recites that “… at least one of the steps of projecting, approximating, and synthesizing is implemented to include advanced error correction, fault-tolerance, and self-healing capabilities.”
The prior art does not show this configuration; therefore this claim contains allowable subject matter.
CONCLUSION
Any inquiry concerning this communication or earlier communications from the examiner should be directed to CARL ADAMS whose telephone number is (571)270-7448. The examiner can normally be reached Monday - Friday, 9AM - 5PM 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, Ke Xiao can be reached at 571-272-7776. 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.
/CARL ADAMS/Examiner, Art Unit 2627
Prosecution Insights