CTNF 19/184,957 CTNF 87510 DETAILED ACTION Notice of Pre-AIA or AIA Status 07-03-aia AIA 15-10-aia 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 07-30-02 AIA 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. 07-34-05 Claims 12, 13, 16 recite the limitation "the tile map". There is insufficient antecedent basis for this limitation in the claims. Claim Rejections - 35 USC § 102 07-06 AIA 15-10-15 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. 07-07-aia AIA 07-07 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 – 07-12-aia AIA (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. 07-15-03-aia AIA Claim 20 is rejected under 35 U.S.C. 102(a)(2) as being anticipated by Kadono et al. (Pub. No. US 2004/0076237 A1) . Regarding claim 20, Kadono discloses One or more memory or storage devices having stored thereon a program ([0247] recording a program implementing the steps of … method to a floppy disk or other computer-readable data recording medium; [0251]; [0257] The software for … can be stored to any computer-readable data recording medium (such as a CD-ROM disc, floppy disk, or hard disk drive)). See MPEP 2111.05 (III), when determining the scope of the claims, “a bitstream of a video” is not given patentable weight, because “a bitstream of a video” is non-functional descriptive material. It is merely static data that imparts no function (unlike an executable computer program which performs a function). It does not have any functional relationship with the intended computer system. Thus, the computer-readable data recording medium disclosed in Kadono meets claim 20 . 07-15-03-aia AIA Claim s 1-2, 4-5, 15-20 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by FINLAY et al. (US 20240354553 A1) . Regarding claims 1, 18-20. FINLAY discloses A method of video processing (abstract, A method for lossy image and video encoding, transmission and decoding), comprising: determining, for a conversion between a video unit of a video and a bitstream of the video (abstract, A method for lossy image and video encoding, transmission and decoding; figure 1, [0213] produce a bitstream 130), a quantization approach of a latent sample based on whether the latent sample and a neighbor quantized latent sample is in a same region (abstract, the sizes of the bins used in the quantization process are based on the input image; [0012] The sizes of the bins used to decode the quantized latent may be based on previously decoded pixels of the quantized latent; [0315] Δ can be predicted as some linear combination of previously-decoded pixels (the region of previously decoded pixels corresponds to a same region)); obtaining, using a neural network, a quantized latent sample comprising a quantized luma latent sample and a quantized chroma latent sample by applying the quantization approach to the latent sample ([0013] The quantisation process may comprise a third trained neural network; [0007] The sizes of the bins may be different between at least two channels of the latent representation; [0009] The quantisation process may comprise performing an operation on the value of each pixel of the latent representation corresponding to the bin size assigned to that pixel; [0201] an image file may have 3 channels, colour spaces or formats include the YCbCr colour models); and performing the conversion based on the quantized latent sample and one of: a synthesis transform network or an analysis transform network (figure 1, [0212] The input image 5 is provided to a trained neural network 110 characterized by a function f.sub.θ acting as an encoder. This output is referred to as a latent representation of the input image 5. In a second step, the latent representation is quantised in a quantisation process 140 characterised by the operation Q, resulting in a quantized latent; [0214] The quantized latent is provided to another trained neural network 120 characterized by a function go acting as a decoder). Regarding claim 2. FINLAY discloses The method of claim 1, wherein obtaining the quantized latent sample comprising the quantized luma latent sample and the quantized chroma latent sample comprises at least one of: in accordance with a determination that a neighbor quantized luma latent sample is in the same region as a luma latent sample, obtaining the quantized luma latent sample using the neighbor quantized luma latent sample ([0012] The sizes of the bins used to decode the quantized latent may be based on previously decoded pixels of the quantized latent (the region of previously decoded pixels corresponds to a same region)); in accordance with a determination that a neighbor quantized chroma latent sample is in the same region as a chroma latent sample, obtaining the quantized chroma latent sample using the neighbor quantized chroma latent sample; in accordance with a determination that a neighbor quantized luma latent sample is not in the same region as a luma latent sample, obtaining the quantized luma latent sample without using the neighbor quantized luma latent sample; in accordance with a determination that a neighbor quantized chroma latent sample is not in the same region as a chroma latent sample, obtaining the quantized chroma latent sample without using the neighbor quantized chroma latent sample; or in accordance with a determination that a neighbor quantized latent sample is not in the same region as the latent sample, obtaining the quantized latent sample based on at least one padded sample. Regarding claim 4. FINLAY discloses The method of claim 1, wherein a quantized latent representation is a tensor comprising a plurality of quantized latent samples, or wherein the quantized latent representation is a matrix comprising the plurality of quantized latent samples ([0009] The quantisation process may comprise performing an operation on the value of each pixel of the latent representation corresponding to the bin size assigned to that pixel). Regarding claim 5. FINLAY discloses The method of claim 1, further comprising at least one of: obtaining a reconstructed image using the quantized luma latent sample and the quantized chroma latent sample with a synthesis transform network, wherein all indices associated with the neighbor quantized latent sample integers; obtaining the latent sample using an analysis transform, wherein a luma component and chroma components of the latent sample employ a set of same analysis transform networks or separated analysis transform networks ([0201] an image file may have 3 channels, colour spaces or formats include the YCbCr colour models; [0319]-[0323] equation (31), C is the number of channels); or determining whether the latent sample and the neighbor quantized latent sample is in a same region based on a tile map or a region map, and wherein the tile map is used to divide the quantized latent representation into a plurality of regions. Regarding claim 15. FINLAY discloses The method of claim 1, wherein luma and chroma components employ different synthesis transforms or the analysis transforms ([0201] an image file may have 3 channels, colour spaces or formats include the YCbCr colour models; [0319]-[0323] equation (31), C is the number of channels). Regarding claim 16. FINLAY discloses The method of claim 1, wherein the tile map is obtained according to a size of the quantized latent representation which is a matrix or tensor that comprises quantized latent samples, and/or wherein the region map is obtained based on a size of the reconstructed image, and/or wherein a tile map is obtained according to depth values that indicates depths of luma and chroma synthesis transforms, and/or wherein the region map is obtained according to depth values of luma transform network and chroma transform network, and/or wherein a probability modeling in entropy coding part utilizes coded group information, and/or wherein the synthesis transform or the analysis transform are wavelet-based transforms, and/or wherein performing the conversion based on the quantized latent sample and the synthesis transform network or the analysis transform network is applied to a first set luma and chroma latent samples, and/or wherein performing the conversion based on the quantized latent sample and the synthesis transform network or the analysis transform network is not applied to a second luma and chroma latent samples, and/or wherein performing the conversion based on the quantized latent sample and the synthesis transform network or the analysis transform network is applied to luma and chroma samples in a first region, and/or wherein performing the conversion based on the quantized latent sample and the synthesis transform network or the analysis transform network is not applied to luma and chroma latent samples in a second region, and/or wherein at least one of: region locations or dimensions is determined depending on color format or color components, and/or wherein at least one of: region locations or dimensions is determined depending on whether a picture is resized, and/or wherein whether and/or how to perform the conversion based on the quantized latent sample and the synthesis transform network or the analysis transform network depends on the latent sample location, and/or wherein whether and/or how to perform the conversion based on the quantized latent sample and the synthesis transform network or the analysis transform network depends on whether the picture is resized, and/or wherein whether and/or how to perform the conversion based on the quantized latent sample and the synthesis transform network or the analysis transform network depends on color format or color components, and/or wherein the neural network is an auto-regressive neural network ([0314] Q can be an auto-regressive neural network). Regarding claim 17. FINLAY discloses The method of claim 1, wherein the conversion includes encoding the video unit into the bitstream, and/or wherein the conversion includes decoding the video unit from the bitstream (abstract, A method for lossy image and video encoding, transmission and decoding; figure 1, [0213] produce a bitstream 130) . 07-15-03-aia AIA Claim s 1, 12-14, 18-20 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Kianfar et al. (US 20210329267 A1) . Regarding claims 1, 18-20. Kianfar discloses A method of video processing (abstract, A video encoder), comprising: determining, for a conversion between a video unit of a video and a bitstream of the video ([0030] Video encoder 200 may generate a bitstream including encoded video data), a quantization approach of a latent sample based on whether the latent sample and a neighbor quantized latent sample is in a same region ([0119] determine the (e.g., locally) optimal quantization levels of a block of transform coefficients; [0142] a local greedy search that exhaustively searches for the lowest cost for each 4×4 coefficient group (a block or coefficient group corresponds to a same region)); obtaining, using a neural network, a quantized latent sample comprising a quantized luma latent sample and a quantized chroma latent sample by applying the quantization approach to the latent sample ([0028] parallelized rate-distortion optimized quantization using deep learning; [0119] An approach described in this disclosure uses deep learning to learn search algorithms via neural network 211 such that with a single forward pass of neural network 211, it may be possible to infer the quantization levels for many transform coefficient blocks in parallel; [0048] a CTU includes a coding tree block (CTB) of luma samples, two corresponding CTBs of chroma samples of a picture that has three sample arrays); and performing the conversion based on the quantized latent sample and one of: a synthesis transform network or an analysis transform network ([0175] video encoder 200 (e.g., quantization unit 208 of quantization unit 208 of video encoder 200) may perform RDOQ using deep learning techniques of this disclosure as part of quantizing the transform coefficients). Regarding claim 12. Kianfar discloses The method of claim 1, wherein the tile map of luma and chroma samples is predetermined ([0049] A tile may be a rectangular region of CTUs within a particular tile column and a particular tile row in a picture). Regarding claim 13. Kianfar discloses The method of claim 1, wherein the tile map is determined based on at least one indication in the bitstream ([0049] A tile column refers to a rectangular region of CTUs having a height equal to the height of the picture and a width specified by syntax elements (e.g., such as in a picture parameter set). A tile row refers to a rectangular region of CTUs having a height specified by syntax elements (e.g., such as in a picture parameter set) and a width equal to the width of the picture). Regarding claim 14. Kianfar discloses The method of claim 13, wherein the at least one indication indicates one or more of: the numbers of tiles in the tile map that divides the latent sample, a size of the tiles in luma latent sample and chroma latent sample, or position of tiles ([0049] A tile column refers to a rectangular region of CTUs having a height equal to the height of the picture and a width specified by syntax elements (e.g., such as in a picture parameter set). A tile row refers to a rectangular region of CTUs having a height specified by syntax elements (e.g., such as in a picture parameter set) and a width equal to the width of the picture) . Claim Rejections - 35 USC § 103 07-06 AIA 15-10-15 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. 07-20-aia AIA 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. 07-23-aia AIA 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. 07-20-02-aia AIA This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention. 07-21-aia AIA Claim s 3, 6-7 are rejected under 35 U.S.C. 103 as being unpatentable over (FINLAY et al. (US 20240354553 A1) or Kianfar et al. (US 20210329267 A1)) in view of Sauer et al. (US 20250142099 A1) . Regarding claim 3. Sauer discloses The method of claim 1, wherein obtaining the quantized latent sample comprising the quantized luma latent sample and the quantized chroma latent sample comprises: obtaining the quantized chroma latent sample using the quantized luma latent sample ([0158] independent coding/processing of the primary color component (e.g. luma component), while the secondary color components (e.g. chroma UV) are conditionally coded/processed, using primary component as auxiliary input; [0013] the first subnetwork and/or the second subnetwork perform one of picture encoding by a convolutional subnetwork; and rate distortion optimization quantization, RDOQ; and picture filtering). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the inventions of (FINLAY or Kianfar) and Sauer, to apply Conditional Color Separation, in order to reduce computational complexity and enable parallel processing. Regarding claim 6. Sauer discloses The method of claim 5, wherein the quantized luma latent sample and the quantized chroma latent sample employ separated synthesis transform networks (figure 25, [0066] luma and chroma components of a tensor are processed separately in multiple pipelines and each pipeline processing separately a plurality of tiles of respective component), and/or wherein the quantized latent representation is divided into 7 regions. Regarding claim 7. Sauer discloses The method of claim 1, wherein the quantized luma latent sample and the quantized chroma latent sample employ an identical partitioning strategy, and/or wherein the quantized luma latent sample and the quantized chroma latent sample employ separated indications for a splitting mode, and/or wherein a luma latent sample employs a wavelet-based transformation style partitioning, and a chroma latent sample does not further split into sub-tiles, and/or wherein a luma latent sample employs a wavelet-based transformation style partitioning, and a chroma latent sample employs the quad-tree partitioning where four identical sub-tiles are generated or a binary-tree partitioning where two identical sub-tiles are generated, and/or wherein a luma latent sample employs a wavelet-based transformation style partitioning, and a chroma latent sample employs a recursive partitioning, wherein a splitting mode and a splitting depth are indicated to a decoder, and/or wherein whether to employ the wavelet-based transformation style partitioning is indicated with one flag, and/or wherein tile partitioning modes are determined according to a quantization parameter or target bitrate, and/or wherein tile maps are applied to the quantized luma latent sample and the quantized chroma latent sample, corresponding outputs are adjusted with tile partitioning ([0330] the first component being luma and the second component being one of chroma U or V, which are processed in separate pipelines. The method comprises processing the first component including dividing the first component in the spatial dimensions into a first plurality of tiles and processing the tiles of the first plurality of tiles separately; and processing the second component including dividing the second component in the spatial dimensions into a second plurality of tiles and processing the tiles of the second plurality of tiles separately) . 07-21-aia AIA Claim s 8-11 are rejected under 35 U.S.C. 103 as being unpatentable over (FINLAY et al. (US 20240354553 A1) or Kianfar et al. (US 20210329267 A1)) in view of Koyuncu et al. (US 20240078414 A1) . Regarding claim 8. Koyuncu discloses The method of claim 1, wherein the quantized latent representation is divided into N tiles, wherein N equals to 3 ([0031] quantizing the latent tensor before separating into patches; [0188]; abstract, separating the latent tensor into patches; [0007] separating the latent tensor into a plurality of patches), luma and chroma latent sample employ 3 tiles partitioning such that the tiles within luma and chroma latent sample are independently processed ([0008] each patch may be processed independently from processing of other patches; [0242] in video coding each pixel is typically represented in a luminance and chrominance format or color space, e.g. YCbCr; [0142] The input image 311 to be compressed is represented as a 3D tensor with the size of H×W×C, where H and W are the height and width of the image and C is the number of color channels). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the inventions of (FINLAY or Kianfar) and Koyuncu, to independently process each patch/tile/color, in order to enable parallel processing. Regarding claim 9. Koyuncu discloses The method of claim 8, wherein a sample belonging to one tile is processed using samples from the same tile, and/or wherein the N tiles are processed in parallel ([0008] perform the entropy encoding in parallel for a plurality of patches). Regarding claim 10. Koyuncu discloses The method of claim 1, wherein all tiles in luma and chroma latent samples are independent from each other (figure 1, channels; [0130] the input image is passed through convolutional layers and becomes abstracted to a feature map comprising several channels, the number of input channels is normally equal to the number of channels of data representation, for instance 3 channels for RGB or YUV representation of images or video). Regarding claim 11. Koyuncu discloses The method of claim 1, wherein only tiles in luma components are independent of each other, and/or wherein luma and chroma latent samples employ N-tiles partitioning, wherein N is an integer number (abstract, separating the latent tensor into patches; [0007] separating the latent tensor into a plurality of patches). Conclusion Any inquiry concerning this communication or earlier communications from the examiner should be directed to XIAOLAN XU whose telephone number is (571)270-7580. The examiner can normally be reached Mon. to Fri. 9am-5pm. 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, SATH V. PERUNGAVOOR can be reached at (571) 272-7455. 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. /XIAOLAN XU/ Primary Examiner, Art Unit 2488 Application/Control Number: 19/184,957 Page 2 Art Unit: 2488 Application/Control Number: 19/184,957 Page 4 Art Unit: 2488 Application/Control Number: 19/184,957 Page 5 Art Unit: 2488 Application/Control Number: 19/184,957 Page 6 Art Unit: 2488 Application/Control Number: 19/184,957 Page 7 Art Unit: 2488 Application/Control Number: 19/184,957 Page 8 Art Unit: 2488 Application/Control Number: 19/184,957 Page 9 Art Unit: 2488 Application/Control Number: 19/184,957 Page 10 Art Unit: 2488 Application/Control Number: 19/184,957 Page 11 Art Unit: 2488 Application/Control Number: 19/184,957 Page 12 Art Unit: 2488 Application/Control Number: 19/184,957 Page 13 Art Unit: 2488 Application/Control Number: 19/184,957 Page 14 Art Unit: 2488 Application/Control Number: 19/184,957 Page 15 Art Unit: 2488
Prosecution Insights