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 20 has been cancelled. Claim 21 has been added. Claims 1-19 and 21 are pending for examination.
Response to Arguments
Applicant's arguments filed 03/02/2026 have been fully considered but they are not persuasive.
Applicant argues that:
In Tjandrasuwita, the budget limits the number of bits that can be encoded from a block, and it is enforced during the run-length encoding of the transformed and quantized data in block. That is, the budget is an upper limit of the number of bits encoded for a block. It is obvious to a POSA that the upper limit does not belong to statistical information.
Examiner respectfully disagrees.
Tjandrasuwita discloses statistical information associated with a representation of the visual data see [0090]: (the "smaller" transformed and quantized values (e.g., those values that do not satisfy the second threshold mentioned above),). “smaller” transformed and quantized values are interpreted by the examiner to indicate statistical information. As taught by Tjandrasuwita, smaller values do not contribute significantly to image fidelity, are discarded (not encoded), also reducing the amount of compressed data while maintaining image fidelity. Discarded values are therefore absent from the bitstream based on a statistical evaluation of being “smaller”.
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 1-19 and 21 are rejected under 35 U.S.C. 103 as being unpatentable over BESENBRUCH (US 20220279183 A1) in view of Tjandrasuwita (US 20060078211 A1).
Regarding claim 1, BESENBRUCH teaches a method for visual data processing, comprising:
obtaining, for a conversion between visual data and a bitstream of the visual data with a neural network (NN)-based model, information associated with a first representation of the visual data ([0092] (ii) the first computer system is configured to encode the input image using the first trained neural network, to produce a latent representation;).
BESENBRUCH does not explicitly teach the following limitations, however, in an analogous art, Tjandrasuwita teaches obtaining statistical information associated with a first representation of the visual data ( [0013] In one embodiment of the present invention, a limit or budget is assigned to each block (e.g., each luminance and chrominance block) of transformed and quantized image data.)
determining at least one sample from a second representation of the visual data based on the statistical information, a value of the at least one sample being absent from the bitstream, the second representation being associated with the first representation ([0090] [0076] In step 707, in the present embodiment, the remaining values in the block (e.g., block 432 of FIG. 4) are not encoded. In effect, the remaining values are discarded by inserting an end-of-block code into the encoded data. Flowchart 700 then proceeds to step 716. Examiner note: additional values of the same block are included on excluded based on a statistical value of the budget/limit); and
performing the conversion based on the determining (Decoding process 224 of FIG. 2 decompresses (reconstructs) the compressed data 223 to generate the reconstructed data 225. [0038]).
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 Tjandrasuwita and apply them to BESENBRUCH. One would be motivated as such as to improve the efficiency of the subsequent encoding by reducing the number of iterations that may be needed (Tjandrasuwita: [0091]).
Regarding claim 2, BESENBRUCH in view of Tjandrasuwita teaches the method of claim 1. BESENBRUCH teaches wherein the first representation comprises a latent representation of the visual data or a residual latent presentation of the visual data (This neural network E( . . . ) produces a latent representation, which we call y. [0824]).
Regarding claim 3, BESENBRUCH in view of Tjandrasuwita teaches the method of claim 1. BESENBRUCH teaches wherein the first representation is generated based on applying a first neural network in the NN-based model to the visual data, and the second representation is obtained by quantizing the first representation (This neural network E( . . . ) produces a latent representation, which we call y. The latent representation is quantized to provide ŷ, a quantized latent. [0824]).
Regarding claim 4, BESENBRUCH in view of Tjandrasuwita teaches the method of claim 1. Tjandrasuwita teaches wherein determining the at least one sample from the second representation comprises determining the at least one sample comprises a sample of the second representation in accordance with a determination that at least one of the following conditions is satisfied: a first statistical value corresponding to the sample is smaller than a first threshold ( as the transformed and quantized values in a block) are encoded and the number of encoded bits are counted, a first threshold (within the budget limit being applied to the block) and a second threshold (corresponding to the size of the values being encoded) can be applied, as described above. [0089]), a value determined based on the first statistical value is smaller than a second threshold , or a probability that a value of the sample is equal to a target value is smaller than a third threshold (the "smaller" transformed and quantized values (e.g., those values that do not satisfy the second threshold mentioned above), which generally do not contribute significantly to image fidelity, are discarded (not encoded), also reducing the amount of compressed data while maintaining image fidelity. [0090]), or
wherein determining the at least one sample from the second representation comprises determining the at least one sample comprises samples in a block of the second representation in accordance with a determination that at least one of the following conditions is satisfied: a first statistical value corresponding to each sample in the block is smaller than a fourth threshold, a first metric is smaller than a fifth threshold, the first metric being determined based on first statistical values corresponding to samples in the block, a probability that a value of each sample in the block is equal to a target value is smaller than a sixth threshold, or a second metric is smaller than a seventh threshold, the second metric being determined based on probabilities that values of samples in the block are equal to respective target values (Wherein clause is claimed as an alternative “or”), or
wherein determining the at least one sample from the second representation comprises determining the at least one sample comprises a sample of the second representation in accordance with a determination that at least one of the following conditions is satisfied: a first statistical value corresponding to the sample is larger than an eighth threshold, a value determined based on the first statistical value is larger than a ninth threshold, or a probability that a value of the sample is equal to a target value is larger than a tenth threshold (Wherein clause is claimed as an alternative “or”), or
wherein determining the at least one sample from the second representation comprises determining the at least one sample comprises samples in a block of the second representation in accordance with a determination that at least one of the following conditions is satisfied: a first statistical value corresponding to each sample in the block is larger than an eleventh threshold, a first metric is larger than a twelfth threshold, the first metric being determined based on first statistical values corresponding to samples in the block, a probability that a value of each sample in the block is equal to a target value is larger than a thirteenth threshold, or a second metric is larger than a fourteenth threshold, the second metric being determined based on probabilities that values of samples in the block are equal to respective target values (Wherein clause is claimed as an alternative “or”).
The same motivation used to combine BESENBRUCH in view of Tjandrasuwita in claim 1 is applicable.
Regarding claim 5, BESENBRUCH in view of Tjandrasuwita teaches the method of claim 4. Tjandrasuwita teaches wherein the first metric is an average, a minimum one or a maximum one of the first statistical values, or the second metric is an average, a minimum one or a maximum one of the probabilities (Wherein clause is claimed as an alternative “or”)., or
wherein a size of the block is N by M, and each of N and M is a positive integer, or
wherein the first statistical value is a variance (The AC values describe the variation from the DC value [0045].).
The same motivation used to combine BESENBRUCH in view of Tjandrasuwita in claim 1 is applicable.
Regarding claim 6, BESENBRUCH in view of Tjandrasuwita teaches the method of claim 5. BESENBRUCH teaches wherein N and M are indicated in the bitstream (Wherein clause is claimed as a conditional alternative “or”).
Regarding claim 7, BESENBRUCH in view of Tjandrasuwita teaches the method of claim 4. Tjandrasuwita teaches wherein a target value of a sample comprises one of the following:
a first predetermined value, or
a second statistical value corresponding to the sample (if the first threshold is reached, then any remaining (e.g., not yet encoded) transformed and quantized values that do not satisfy a second threshold are set to zero (in effect, they are discarded). [0016] Examiner note: zero is a predetermined value).
The same motivation used to combine BESENBRUCH in view of Tjandrasuwita in claim 1 is applicable.
Regarding claim 8, BESENBRUCH in view of Tjandrasuwita teaches the method of claim 7. Tjandrasuwita teaches wherein the first predetermined value is zero, or the second statistical value is a mean (if the first threshold is reached, then any remaining (e.g., not yet encoded) transformed and quantized values that do not satisfy a second threshold are set to zero (in effect, they are discarded). [0016] Examiner note: zero is a predetermined value).
The same motivation used to combine BESENBRUCH in view of Tjandrasuwita in claim 1 is applicable.
Regarding claim 9, BESENBRUCH in view of Tjandrasuwita teaches the method of claim 4. Tjandrasuwita teaches wherein the probability is determined based on the statistical information, or
wherein at least one of the following thresholds is indicated in the bitstream: the first threshold, the second threshold, the third threshold, the fourth threshold, the fifth threshold, the sixth threshold, the seventh threshold, the eighth threshold, the ninth threshold, the tenth threshold, the eleventh threshold, the twelfth threshold, the thirteenth threshold, or the fourteenth threshold (Fig. 7: first and second threshold must be available to encoder/decoder).
The same motivation used to combine BESENBRUCH in view of Tjandrasuwita in claim 1 is applicable.
Regarding claim 10, BESENBRUCH in view of Tjandrasuwita teaches the method of claim 1. Tjandrasuwita teaches wherein performing the conversion comprises:
reconstructing the second representation based on the at least one sample; and
performing the conversion based on the reconstructed second representation (Decoding process 224 of FIG. 2 decompresses (reconstructs) the compressed data 223 to generate the reconstructed data 225. [0038]).
The same motivation used to combine BESENBRUCH in view of Tjandrasuwita in claim 1 is applicable.
Regarding claim 11, BESENBRUCH in view of Tjandrasuwita teaches the method of claim 10. BESENBRUCH teaches wherein the at least one sample comprises all samples of the second representation, and reconstructing the second representation comprises determining values of the at least one sample to reconstruct the second representation, or
wherein the second representation comprises the at least one sample and a first set of samples different from the at least one sample, and reconstructing the second representation comprises: determining values of the at least one sample; obtaining values of the first set of samples by performing entropy decoding process on the bitstream based on the statistical information; and reconstructing the second representation based on the values of the first set of samples and the determined values of the at least one sample (The recipient device entropy decodes the bitstream to provide ŷ, and then uses the decoder which is a library installed on a recipient device (e.g. laptop computer, desktop computer, smart phone) to provide the output image {circumflex over (x)}.).
Regarding claim 12, BESENBRUCH in view of Tjandrasuwita teaches the method of claim 11. Tjandrasuwita teaches wherein determining values of the at least one sample comprises: determining a value of each sample of the at least one sample to be a second predetermined value or a third statistical value corresponding to the sample (if the first threshold is reached, then any remaining (e.g., not yet encoded) transformed and quantized values that do not satisfy a second threshold are set to zero (in effect, they are discarded). [0016]).
The same motivation used to combine BESENBRUCH in view of Tjandrasuwita in claim 1 is applicable.
Regarding claim 13, BESENBRUCH in view of Tjandrasuwita teaches the method of claim 10. BESENBRUCH teaches wherein the first representation is a latent representation of the visual data, and performing the conversion based on the reconstructed second representation comprises: reconstructing the visual data by performing a synthesis transform on the reconstructed second representation (This neural network E( . . . ) produces a latent representation, which we call y. The latent representation is quantized to provide ŷ, a quantized latent. The quantized latent goes to another neural network characterized by a function D( . . . ) which is a decoder. The decoder provides an output image, which we call {circumflex over (x)}. [0824]), or
wherein the first representation is a residual latent representation of the visual data, and performing the conversion comprises: generating a quantized latent representation of the visual data based on the reconstructed second representation and a fourth statistical value comprised in the statistical information; and reconstructing the visual data by performing a synthesis transform on the quantized latent representation (Wherein clause is claimed as an alternative “or”).
Regarding claim 14, BESENBRUCH in view of Tjandrasuwita teaches the method of claim 13. Tjandrasuwita teaches wherein the fourth statistical value is a mean ( In transformed block 431, the first value (e.g., the value in the upper left corner of block 431) is referred to as the DC value (this value establishes the average brightness). The remaining values in block 431 are referred to as the AC values. The AC values describe the variation from the DC value.).
The same motivation used to combine BESENBRUCH in view of Tjandrasuwita in claim 1 is applicable.
Regarding claim 15, BESENBRUCH in view of Tjandrasuwita teaches the method of claim 1. BESENBRUCH teaches wherein the statistical information is generated by using a second neural network in the NN-based model, and the second neural network comprises a hyper scale decoder subnetwork for generating a variance (The decoder then decodes bitstream.sub.{circumflex over (z)} first, then executes the hyper decoder, to obtain the distribution parameters (μ, σ), then the distribution parameters (μ, σ) are used with bitstream.sub.ŷ to decode the ŷ, which are then executed by the decoder to get the output image {circumflex over (x)}. [0869]).
Regarding claim 16, BESENBRUCH in view of Tjandrasuwita teaches the method of claim 1. BESENBRUCH teaches wherein at least one of the following is indicated in the bitstream: information on whether to apply the method, or information on how to apply the method, or
wherein at least one of the following is dependent on a color format and/or a color component of the visual data: information on whether to apply the method, or information on how to apply the method, or
wherein a value included in the bitstream is coded at one of the following: a sequence level, a picture level, a slice level, or a block level ([0046] The method may be one in which an autoregressive model is an Intrapredictions, Neural Intrapredictions and block-level model, or a filter-bank model, or a parameters from Neural Networks model, or a Parameters derived from side-information model, or a latent variables model, or a temporal modelling model.), or
wherein a value included in the bitstream is binarized before being coded, or wherein a value included in the bitstream is coded with at least one arithmetic coding context, or
wherein the visual data comprise a picture of a video or an image.
Regarding claim 17, BESENBRUCH in view of Tjandrasuwita teaches the method of claim 1. BESENBRUCH teaches wherein the conversion includes encoding the visual data into the bitstream, or wherein the conversion includes decoding the visual data from the bitstream (Fig. 1: decoder and bitstream).
Regarding claim 18, BESENBRUCH teaches an apparatus for visual data processing comprising a processor and a non-transitory memory with instructions thereon, wherein the instructions upon execution by the processor ([0165] According to a sixth aspect of the invention, there is provided a computer program product for training a first neural network and a second neural network, the neural networks being for use in lossy image or video compression, transmission and decoding, the computer program product executable on a processor), cause the processor to perform acts comprising:
obtaining, for a conversion between visual data and a bitstream of the visual data with a neural network (NN)-based model, information associated with a first representation of the visual data ([0092] (ii) the first computer system is configured to encode the input image using the first trained neural network, to produce a latent representation;).
BESENBRUCH does not explicitly teach the following limitations, however, in an analogous art, Tjandrasuwita teaches obtaining statistical information associated with a first representation of the visual data ( [0013] In one embodiment of the present invention, a limit or budget is assigned to each block (e.g., each luminance and chrominance block) of transformed and quantized image data.)
determining at least one sample from a second representation of the visual data based on the statistical information, a value of the at least one sample being absent from the bitstream, the second representation being associated with the first representation ([0076] In step 707, in the present embodiment, the remaining values in the block (e.g., block 432 of FIG. 4) are not encoded. In effect, the remaining values are discarded by inserting an end-of-block code into the encoded data. Flowchart 700 then proceeds to step 716. Examiner note: additional values of the same block are included on excluded based on a statistical value of the budget/limit); and
performing the conversion based on the determining (Decoding process 224 of FIG. 2 decompresses (reconstructs) the compressed data 223 to generate the reconstructed data 225. [0038]).
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 Tjandrasuwita and apply them to BESENBRUCH. One would be motivated as such as to improve the efficiency of the subsequent encoding by reducing the number of iterations that may be needed (Tjandrasuwita: [0091]).
Regarding claim 19, BESENBRUCH teaches a non-transitory computer-readable storage medium storing instructions that cause a processor to perform acts ([0165] According to a sixth aspect of the invention, there is provided a computer program product for training a first neural network and a second neural network, the neural networks being for use in lossy image or video compression, transmission and decoding, the computer program product executable on a processor) comprising:
obtaining, for a conversion between visual data and a bitstream of the visual data with a neural network (NN)-based model, information associated with a first representation of the visual data ([0092] (ii) the first computer system is configured to encode the input image using the first trained neural network, to produce a latent representation;).
BESENBRUCH does not explicitly teach the following limitations, however, in an analogous art, Tjandrasuwita teaches obtaining statistical information associated with a first representation of the visual data ( [0013] In one embodiment of the present invention, a limit or budget is assigned to each block (e.g., each luminance and chrominance block) of transformed and quantized image data.)
determining at least one sample from a second representation of the visual data based on the statistical information, a value of the at least one sample being absent from the bitstream, the second representation being associated with the first representation ([0076] In step 707, in the present embodiment, the remaining values in the block (e.g., block 432 of FIG. 4) are not encoded. In effect, the remaining values are discarded by inserting an end-of-block code into the encoded data. Flowchart 700 then proceeds to step 716. Examiner note: additional values of the same block are included on excluded based on a statistical value of the budget/limit); and
performing the conversion based on the determining (Decoding process 224 of FIG. 2 decompresses (reconstructs) the compressed data 223 to generate the reconstructed data 225. [0038]).
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 Tjandrasuwita and apply them to BESENBRUCH. One would be motivated as such as to improve the efficiency of the subsequent encoding by reducing the number of iterations that may be needed (Tjandrasuwita: [0091]).
Regarding claim 21, the method of claim 21 is rejected under the same arts and evidence used to reject claims 1.
Conclusion
THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
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