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 § 112
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claims 17 – 20 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the enablement requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to enable one skilled in the art to which it pertains, or with which it is most nearly connected, to make and/or use the invention.
Claim 17 recites a means-plus-function limitation. The long-recognized problem with a single means claim is that it covers every conceivable means for achieving the stated result, while the specification discloses at most only those means known to the inventor.
Claims 18 – 20 are dependent claims for claim 17, thus, they are rejected accordingly.
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.
Claim(s) 1, 4 – 5, 7, 9, 12 – 13, 15 – 17 and 19 – 20 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Jiang et al. (US Patent Application Publication 2019/0138889, IDS), hereinafter referred as Jiang.
Regarding claim 9, Jiang discloses at least one processor (Fig. 3, [0073]) comprising:
one or more processing units (Fig. 3, #350) to:
determine, using a neural network, a plurality of motion characteristics for at least a first set of pixels in a first frame and a corresponding second set of pixels in a second frame of a video sequence (Fig. 1F, steps 162 – 165, [0054]);
generate, for an intermediate frame to be generated at a point in the sequence of frames between the first frame and the second frame, a first candidate frame based in part on the motion characteristics applied, in a first direction, to pixels of the first frame (Fig. 1F, steps 170 – 180, [0055], generate forward warping frame from first frame);
generate, for the intermediate frame, a second candidate frame based on the motion characteristics applied, in an opposite direction, to pixels of the second frame (Fig. 1F, steps 170 – 180, [0055], generate backward warping frame from second frame);
generate the intermediate frame between the first frame and the second frame by aligning and blending the first candidate frame and the second candidate frame (Fig. 1F, steps 190, [0056], generate final intermediate frame from warped frames; also shown in Fig. 1E; [0042 – 0052] and equations show aligning and blending the first candidate frame and the second candidate frame); and
provide the generated intermediate frame for display on a display device ([0073] display).
Regarding claim 12 (depends on claim 9), Jiang discloses the processor wherein generating the first candidate frame and the second candidate frames comprises warping, respectively, the first set of pixels from the first frame and the second set of pixels from the second frame to an intermediate position based on the plurality of motion characteristics (Fig. 1F, steps 170 – 180, [0055], forward and backward warping).
Regarding claim 13 (depends on claim 9), Jiang discloses the processor wherein an optical flow model is used to determine additional motion characteristics and the first candidate frame and the second candidate frames are further generated based on the additional motion characteristics determined based on the optical flow model (Fig. 1E; [0042 – 0052]).
Regarding claim 15 (depends on claim 9), Jiang discloses the processor wherein generating the intermediate frame further comprises: aligning, using a second neural network, the first candidate frame and the second candidate frame; and blending, using the second neural network the aligned first candidate frame and second candidate frame to produce the intermediate frame ([0042 – 0052] and equations show aligning and blending the first candidate frame and the second candidate frame).
Regarding claim 16 (depends on claim 9), Jiang discloses the processor wherein the processor is included in a system comprising at least one of: a system for performing simulation operations;
a system for performing simulation operations to test or validate autonomous machine applications;
a system for performing digital twin operations;
a system for performing light transport simulation;
a system for rendering graphical output;
a system for performing deep learning operations ([0129 – 0133]);
a system implemented using an edge device;
a system for generating or presenting virtual reality (VR) content;
a system for generating or presenting augmented reality (AR) content;
a system for generating or presenting mixed reality (MR) content;
a system incorporating one or more Virtual Machines (VMs);
a system implemented at least partially in a data center;
a system for performing hardware testing using simulation;
a system for synthetic data generation;
a system for performing generative AI operations;
a system implemented using one or more large language model (LLMs),
a system implemented using one or more vision language model (VLMs);
a system implemented using one or more multi-modal language models;
a system using or deploying one or more inference microservices;
a system that incorporates one or more machine learning models deployed in a service or microservice along with an OS-level virtualization package (e.g., a container); a collaborative content creation platform for 3D assets; or
a system implemented at least partially using cloud computing resources (the rest of limitations can be ignored because of “or”).
Regarding claims 1, 4 – 5 and 7, they are corresponding to claims 9, 12 – 13 and 15, respectively, thus, they are interpreted and rejected for the same reason set forth for claims 9, 12 – 13 and 15.
Regarding claim 17, Jiang discloses a system (Fig. 3, [0073]), comprising:
one or more processing units (Fig. 3, #350) to generate an intermediate frame between a first frame and a second frame (Fig. 1F, step 190, [0056]) based in part on a first candidate frame generated based on the first frame and a second candidate frame generated based the second frame (Fig. 1F, step 162 - 180, [0053 - 0055], warped frames generated), the first and second candidate frames generated using a plurality of motion characteristics determined by a neural network to take (Fig. 1E, [0044 – 0052], using optical flow as input), as input, a first set of pixels in the first frame and a second corresponding set of pixels in the second frame (Fig. 1E, wherein I0 and I1 are a first set of pixels in the first frame and a second corresponding set of pixels in the second frame), and output one or more classification results for the first set of pixels and the second set of pixels (Fig. 1E, [0049], generate predicted (classified) result; also [0129 – 0133] mentioned about classification).
Regarding claims 19 and 20, they are corresponding to claims 12 and 16, respectively, thus, they are interpreted and rejected for the same reason set forth for claims 12 and 16.
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.
Claim(s) 2 – 3, 6, 10 – 11, 14 and 18 is/are rejected under 35 U.S.C. 103 as being unpatentable over Jiang in view of Choe et al. (US Patent Application Publication 2022/0303495, IDS), hereinafter referred as Choe.
Regarding claim 10 (depends on claim 9), Jiang discloses the processor wherein the one or more processing units are further to:
classify, using the neural network, the first set of pixels and the second set of pixels ([0129 – 0133] mentioned about classification).
However, Jiang fails to explicitly disclose wherein the neural network outputs a confidence score for at least one pixel that indicates a degree of reliability of one or more motion vectors associated with the at least one pixel, wherein the determination of the plurality of motion characteristics is based on results of the classification for the at least one pixel.
However, in a similar field of endeavor Choe discloses a method for processing video frames using neural network (abstract, [0048]). In addition, Choe discloses the method wherein the neural network outputs a confidence score for at least one pixel that indicates a degree of reliability of one or more motion vectors associated with the at least one pixel, wherein the determination of the plurality of motion characteristics is based on results of the classification for the at least one pixel ([0058]).
Therefore, 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 invention of Jiang, and wherein the neural network outputs a confidence score for at least one pixel that indicates a degree of reliability of one or more motion vectors associated with the at least one pixel, wherein the determination of the plurality of motion characteristics is based on results of the classification for the at least one pixel. The motivation for doing this is to that the motion determination can be more accurate.
Regarding claim 11 (depends on claim 9), Jiang discloses the processor wherein the one or more processing units are further to: classify, using the neural network, the first set of pixels and the second set of pixels ([0129 – 0133] mentioned about classification).
However, Jiang fails to explicitly disclose wherein the neural network outputs a static confidence score for at least one pixel, the confidence score indicating a likelihood that the pixel corresponds to static content.
However, in a similar field of endeavor Choe discloses a method for processing video frames using neural network (abstract, [0048]). In addition, Choe discloses the method wherein the neural network outputs a static confidence score for at least one pixel, the confidence score indicating a likelihood that the pixel corresponds to static content ([0058]).
Therefore, 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 invention of Jiang, and wherein the neural network outputs a static confidence score for at least one pixel, the confidence score indicating a likelihood that the pixel corresponds to static content. The motivation for doing this is to that the static content determination can be more accurate.
Regarding claim 14 (depends on claim 13), Jiang discloses the processor wherein the blending of the first candidate frame and the second candidate frame includes applying a plurality of blending weights calculated based on confidence scores of the pixels ([0043, 0133], the weights are adjusted for each feature during a backward propagation phase until the DNN correctly labels the input and other inputs in a training dataset; implicitly DNN adjust weight based on confidence scores).
Choe further discloses the confidence scores indicating a likelihood that the pixels correspond to static content ([0058]).
There was some teaching, suggestion, or motivation, either in Jiang or in the knowledge generally available to one of ordinary skill in the art, to modify reference or to combine reference teachings.
There was reasonable expectation of success to achieve claimed limitations by modifying reference or to combine reference teachings (KSR scenario G).
Therefore, 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 invention of Jiang, and applying a plurality of blending weights calculated based on confidence scores of the pixels, the confidence scores indicating a likelihood that the pixels correspond to static content. The motivation for doing this is to that the result generated can be more accurate.
Regarding claims 2, 3 and 6, they are corresponding to claims 10, 11 and 14, respectively, thus, they are interpreted and rejected for the same reason set forth for claims 10, 11 and 14.
Regarding claim 18, it is corresponding to claim 10, thus, they are interpreted and rejected for the same reason set forth for claim 10.
Claim(s) 8 is/are rejected under 35 U.S.C. 103 as being unpatentable over Jiang.
Regarding claim 8 (depends on claim 1), Jiang discloses the computer-implemented method further comprising:
storing data associated with the classification and the motion characteristics for reuse across multiple intermediate frames between the first frame and the second frame ([0075, 0079, 0083, 0089, 0091 – 0099, 0108 – 0114] talked about memory, it is apparent that all data associated with the classification and the motion characteristics are stored/buffered for reuse across multiple intermediate frames between the first frame and the second frame).
It is obvious that Jiang teaches generating additional intermediate frames between the first frame and the second frame, each additional intermediate frame being generated using the stored data.
Jiang discloses that generating additional intermediate frames between the first frame and the second frame (Fig. 1A – 1F, additional intermediate frames can be generated by further select first image and second image). Jiang also discloses memory storing data associated ([0075, 0079, 0083, 0089, 0091 – 0099, 0108 – 0114] talked about memory, it is apparent that all data associated with the classification and the motion characteristics are stored/buffered for reuse across multiple intermediate frames between the first frame and the second frame).
There was some teaching, suggestion, or motivation, either in Jiang or in the knowledge generally available to one of ordinary skill in the art, to modify Jiang or to combine reference teachings.
There was reasonable expectation of success to achieve “generating additional intermediate frames between the first frame and the second frame, each additional intermediate frame being generated using the stored data” by modifying Jiang or to combine reference teachings (KSR scenario G).
Therefore, 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 invention of Jiang, and generating additional intermediate frames between the first frame and the second frame, each additional intermediate frame being generated using the stored data. The motivation for doing this is to take an advantage of using available resources to perform further results based on requirement.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to QIAN YANG whose telephone number is (571)270-7239. The examiner can normally be reached on Monday-Thursday 8am-6pm.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Andrew Bee can be reached on 571-270-5183. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300. 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). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/QIAN YANG/
Primary Examiner, Art Unit 2677
Prosecution Insights