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 .
Claims 1-22 have been cancelled. Claims 23-42 have been added and are pending for examination.
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 23-38 are rejected under 35 U.S.C. 103 as being unpatentable over Chen (US 20220198607 A1) in view Chou (US 20190075301 A1).
Regarding claim 23, Chen teaches a video processing system comprising:
an upsampler (The endpoint application 190 performs any number (including none) and/or types of sampling operations (e.g., upsampling operations or downsampling operations) on the decoded video chunk to generate a reconstructed video chunk 192 having the same resolution as the display device 182. [0048]);
a machine learning (ML) model-based video downsampler trained using a plurality of perceptual loss functions ([0015] FIG. 5 is a flow diagram of method steps for generating a trained downsampling convolutional neural network, according to various embodiments; The iteration error 270 can be any value for any type of overall objective function (e.g., an overall loss function)); and
a processing hardware configured to:
receive an input video sequence having a first display resolution (a first source image having a first resolution [0150]);
map, using the trained ML model-based video downsampler, the content sample to a lower resolution sample (Each of the trained downsampling CNNs maps source images to downsampled image representations having resolutions that are lower that the source image by the associated downsampling factor. [0022] Fig.3 mapping to a lower resolution);
transform, using one of a video codec or a neural network-based (NN-based) proxy video codec, the lower resolution sample into a decoded sample bitstream (Fig. 1: [0047] For explanatory purposes only, FIG. 1 depicts an encoded video chunk 172 that is a chunk of one of the encoded videos 148 that is selected and streamed to the client device 180 at a particular point in time);
predict, using the upsampler and the decoded sample bitstream, an output sample corresponding to the content sample (executing an upsampling algorithm on the first downsampled image to generate a first reconstructed image having the first resolution [0150] Fig. 2: upsampling and reconstructing image from downsampled image); and
modify, based on the predicted output sample, one or more parameters of the trained ML model-based video downsampler (updating at least one parameter of the first convolutional neural network based on the first reconstruction error to generate a trained convolutional neural network. [0150]).
Chen does not teach the following limitations, however, in an analogous art, Chou extract a content sample of the input video sequence (the machine learning block may provide content analysis used to adaptively adjust encoding parameters and/or decoding parameters.).
It would have been obvious for a person of ordinary skill in the art, before the effective filling date of the claimed invention, to take the teachings of Chou and apply them to Chen. One would be motivated as such as to facilitate improving encoding efficiency (Chou: [Abstract]).
Regarding claim 24, Chen in view of Chou teaches the video processing system of claim 23. Chen teaches wherein the lower resolution sample is transformed into the decoded sample bitstream using the NN-based proxy video codec ([0074] More specifically, the configurable non-integer factor CNN 202 maps a given source image to an upsampled image (not shown in FIG. 2) and then maps the upsampled image to the downsampled image representation 248. The upsampled image has a resolution that is higher than the source image by a first configurable factor, and the downsampled image representation 248 has a resolution that is lower than the upsampled image by a second configurable factor.).
Regarding claim 25, Chen in view of Chou teaches the video processing system of claim 24. Chen teaches wherein the NN-based proxy video codec is differentiable (The training application 130 configures a differentiable upsampling algorithm (not shown) to upsample the downsampled image representation by the downsampling factor 124 to generate the reconstructed image. [0060]).
Regarding claim 26, Chen in view of Chou teaches the video processing system of claim 23. Chen teaches wherein the lower resolution sample is transformed into the decoded sample bitstream using the video codec ([0047] For explanatory purposes only, FIG. 1 depicts an encoded video chunk 172 that is a chunk of one of the encoded videos 148 that is selected and streamed to the client device 180 at a particular point in time… [0065] As described previously herein, upon receiving each of the encoded video chunks 172, the endpoint application 190 decodes the encoded video chunk 172 to generate a decoded video chunk (not shown).).
Regarding claim 27, Chen in view of Chou teaches the video processing system of claim 23. Chen teaches wherein modifying the one or more parameters of the trained ML model-based video downsampler renders the trained ML model-based video downsampler content adaptive (The training application then updates the parameters of the downsampling CNN such that the residuals generated by the updated downsampling CNN mitigate the reconstruction error. [0028]).
Regarding claim 28, Chen in view of Chou teaches the video processing system of claim 23. Chen teaches wherein the trained ML model-based video downsampler is configured to support arbitrary scaling factors (FIG. 3 depicts the trained downsampling CNN 140(1) of FIG. 1 that is associated with the downscaling factor 124(1) that can be any non-integer. [0097]).
Regarding claim 29, Chen in view of Chou teaches the video processing system of claim 23. Chen teaches wherein the ML model-based video downsampler is further configured to receive a plurality of weighting factors included in a weighted sum of the plurality of perceptual loss functions, and wherein the ML model-based video downsampler is trained further using the plurality of weighting factors (configurable non-integer factor CNN 202 includes, without limitation, one set of parameters (e.g., weights and biases) that can be trained to modify the mapping from the source image to the upsampled image and another set of parameters that can be trained to modify the mapping from the upsampled image to the downsampled image representation 248. [0077]).
Regarding claim 30, Chen in view of Chou teaches the video processing system of claim 23. Chen teaches wherein the upsampler comprises an ML model-based upsampler (Fig. 2: the configuration engine 210 configures the upsampling engine 250 to upsample by the downsampling factor 124(1). [0081]).
Regarding claims 31-38, the method of claims 31-38 are rejected under the same arts and evidence used to reject the video processing system of claims 23-30.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to HESHAM K ABOUZAHRA whose telephone number is (571)270-0425. The examiner can normally be reached M-F 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, Jamie Atala can be reached at 57127227384. 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.
/HESHAM K ABOUZAHRA/Primary Examiner, Art Unit 2486
Prosecution Insights