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 § 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 1-4, 13, 15-20, are rejected under 35 U.S.C. 103 as being unpatentable over Schroers et al., hereinafter referred to as Schroers (US 2020/0077065 A1) in view of Yin et al., hereinafter referred to as Yin (US 2025/0211799 A1).
As per claim 1, Schroers discloses a method for video processing (Schroers: Abstract.), comprising:
performing a conversion between a video and a bitstream of the video (Schroers: Para. [0018] discloses “video source may be an encoder providing compressed video [claimed bitstream of the video] to video processing system 100 in the form of video data 130 [claimed bitstream of the video] … computing platform 102 of video processing system 100 may function as a video decoder for decompressing [claimed performing a conversion] and colorizing video [claimed video]”),
wherein a neural-network post-processing filter (NNPF) is applied on at least one picture associated with the video (Schroers: Para. [0010] discloses “the present video processing solution utilizes a convolutional neural network (CNN) [claimed neural-network post-processing filter (NNPF)] … to determine an estimated colorization for each frame [claimed applied on at least one picture] of the video sequence [claimed associated with the video]”), and
However, Schroers does not explicitly disclose “… if a color format of the at least one picture is a first color format without a chroma component, at least one indication associated with a chroma input tensor for the NNPF is absent from the bitstream.”
Further, Yin is in the same field of endeavor and teaches if a color format of the at least one picture is a first color format without a chroma component, at least one indication associated with a chroma input tensor for the NNPF is absent from the bitstream (Yin: Para. [0041] (Table 5) and Para. [0070] (Table 19) disclose syntax wherein “packing_format_idc” [claimed indication associated with a chroma input tensor] is conditioned on “If (( input_chroma_format_idc == 1 || input_chroma_format_idc == 2) && nnpf_joint_model_flag)”, implying that if a color format without a chroma component is used (failing the condition), the indication is absent from the bitstream.).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, and having the teachings of Schroers and Yin before him or her, to modify the encoding decoding structure of Schroers to include the conditional presence/absence of chroma input tensor indications feature as described in Schroers. The motivation for doing so would have been to improve bitstream signaling efficiency by providing a configuration that enables conditional-based component syntax formatting.
As per claim 2, Schroers-Yin disclose the method of claim 1, wherein the first color format comprises monochrome or 4:0:0 format (Schroers: Para. [0010] discloses “a video sequence in gray scale [claimed first color format comprises monochrome or 4:0:0 format] beginning with the key video frame.”).
As per claim 3, Schroers-Yin disclose the method of claim 1, wherein the at least one indication comprises at least one of the following:
a first indication indicating a bit depth of a chroma sample value in the input tensor (Yin: Para. [0087] Table 21 discloses “nnpfc_inp_tensor_bitdepth_minus8 [claimed first indication indicating a bit depth of a chroma sample value in the input tensor]”),
at least one second indication indicating at least one of a chroma type or a chroma value used for padding (Yin: Para. [0041] Table 5 discloses “input_chroma_format_idc [claimed second indication indicating a chroma type]” and Yin: Para. [0043] Table 9 discloses “picture_padding_type [claimed chroma value used for padding]”).
As per claim 4, Schroers-Yin disclose the method of claim 3, wherein the first indication comprises a syntax element nnpfc_inp_tensor_chroma_bitdepth_minus8, or
the at least one second indication comprises at least one of a syntax element nnpfc_cb_padding_val or a syntax element nnpfc_cr_padding_val (Yin: Para. [0087] Table 21 discloses “nnpfc_inp_tensor_bitdepth_minus8 [claimed first indication indicating a bit depth of a chroma sample value in the input tensor]”).
As per claim 13, Schroers-Yin disclose the method of claim 1, wherein if an output order of samples from the NNPF indicates no chroma matrix is present in an output tensor of the NNPF, a sixth indication indicating a bit depth of a chroma sample value in the output tensor is not present in the bitstream, or
wherein in the bitstream, a seventh indication indicating an output order of samples from the NNPF precedes at least one of the following: a fifth indication indicating a bit depth of a luma sample value in an output tensor of the NNPF, or a sixth indication indicating a bit depth of a chroma sample value in an output tensor of the NNPF, or
wherein if a bit depth of a sample value in a color component of an output tensor of the NNPF is greater than a bit depth of a sample value in a corresponding color component of an input tensor of the NNPF, a bit depth of a sample value in each of other components of the output tensor is greater than or equal to a bit depth of a sample value in a corresponding color component of the input tensor (Yin: Para. [0087] (Table 21) & [0090]-[0097] disclose syntax order where nnpfc_out_order_idc [claimed seventh indication indicating an output order of samples from the NNPF] appears before nnpfc_inp_tensor_bitdepth_minus8 [claimed fifth indication indicating a bit depth of a luma sample value in an output tensor] and nnpfc_out_tensor_bitdepth_minus8 [claimed sixth indication indicating a bit depth of a chroma sample value in an output tensor].).
As per claim 15, Schroers-Yin disclose the method of claim 1, wherein the bitstream comprises a ninth indication indicating whether a location of a chroma sample in an output of the NNPF is present in the bitstream, or
wherein if a location of a chroma sample in an output of the NNPF is not present in an NNPF Supplemental Enhancement Information (SEI) message in the bitstream, the location of the chroma sample is the same as a location of a chroma sample indicated in video usability information (VUI) in the bitstream, or
wherein the at least one picture comprises at least one decoded picture or at least one cropped decoded picture of the video (Yin: Para. [0014] discloses the general NNPF metadata processing for decoded images.).
As per claim 16, Schroers-Yin disclose the method of claim 1, wherein the conversion includes encoding the video into the bitstream (Schroers: Para. [0018] discloses “video source may be an encoder providing compressed video to video processing system 100 in the form of video data 130 [claimed conversion includes encoding the video into the bitstream]”).
As per claim 17, Schroers-Yin disclose the method of claim 1, wherein the conversion includes decoding the video from the bitstream (Schroers: Para. [0018] discloses “video source may be an encoder providing compressed video to video processing system 100 in the form of video data 130 … computing platform 102 of video processing system 100 may function as a video decoder for decompressing [claimed conversion includes decoding the video from the bitstream] and colorizing video”).
As per claims 18-20, the claim(s) recites analogous limitations to claim(s) 1 above, and is/are therefore rejected on the same premise.
Claims 11-12 are rejected under 35 U.S.C. 103 as being unpatentable over Schroers in view of Yin in further view of Deshpande (US 2024/0205462 A1).
As per claim 11, Schroers-Yin disclose the method of claim 1 (Schroers: Abstract.),
However, Schroers-Yin do not explicitly disclose “… wherein if an output order of samples from the NNPF indicates no luma matrix is present in an output tensor of the NNPF, a fifth indication indicating a bit depth of a luma sample value in the output tensor is not present in the bitstream.”
Further, Deshpande is in the same field of endeavor and teaches wherein if an output order of samples from the NNPF indicates no luma matrix is present in an output tensor of the NNPF, a fifth indication indicating a bit depth of a luma sample value in the output tensor is not present in the bitstream (Deshpande: Para. [0138] & Table 10 disclose “nnpfc_out_tensor_bitdepth_minus8 plus 8 specifies the bit depth [claimed indicating a bit depth] of sample values [claimed luma sample value] in the output integer tensor” and when nnpfc_out_order_idc is 1, indicates “Only the chroma matrices are present in the output tensor [claimed no luma matrix is present in an output tensor of the NNPF]”.).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, and having the teachings of Schroers-Yin and Deshpande before him or her, to modify the encoding decoding NNPF system of Schroers-Yin to include the no luma matrix is present indication feature as described in Deshpande. The motivation for doing so would have been to improve bitstream conformity by providing a configuration that enables extended syntax signaling associated with color formats.
As per claim 12, Schroers-Yin-Deshpande disclose the method of claim 11, wherein the output order of the samples is indicated by a syntax element nnpfc_out_order_idc, or
the fifth indication comprises a syntax element nnpfc_out_tensor_luma_bitdepth_minus8 (Deshpande: Para. [0138] & Table 10 disclose the output order of the samples is indicated by a syntax element “nnpfc_out_order_idc”.).
Claim 14 is rejected under 35 U.S.C. 103 as being unpatentable over Schroers in view of Yin in further view of Tomohiro et al., hereinafter referred to as Tomohiro (WO 2024/142580 A1).
As per claim 14, Schroers-Yin disclose the method of claim 1 (Schroers: Abstract.),
However, Schroers-Yin do not explicitly disclose “… if a purpose of the NNPF comprises colorization of the at least one picture, the bitstream comprises an eighth indication indicating a color format of an output of the NNPF.”
Further, Tomohiro is in the same field of endeavor and teaches if a purpose of the NNPF comprises colorization of the at least one picture, the bitstream comprises an eighth indication indicating a color format of an output of the NNPF (Tomohiro: Para. [0101] discloses “if the value of (nnpfc_purpose & 0x20) is not 0, it indicates that colorization [claimed purpose of NNPF comprises colorization] is performed” and Tomohiro: Para. [0133] discloses “nnpfc_out_colour_format_idc specifies the output colour format [claimed eighth indication indicating a color format of an output of the NNPF].”).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, and having the teachings of Schroers-Yin and Tomohiro before him or her, to modify the encoding decoding structure of Schroers-Yin to include the colorization indication feature as described in Tomohiro. The motivation for doing so would have been to improve coding efficiency by providing a configuration that enables precise bitstream parsing and flexible support for neural network filtering.
Allowable Subject Matter
Claims 5-10 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.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure and can be viewed in the list of references.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to PEET DHILLON whose telephone number is (571)270-5647. The examiner can normally be reached M-F: 5am-1:30pm.
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, 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.
/PEET DHILLON/Primary Examiner
Art Unit: 2488
Date: 09-11-2026
Prosecution Insights