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 .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 3/30/2026 has been entered.
Response to Arguments
Applicant’s arguments, see pages 9-10, filed 3/30/2026, with respect to the rejection of claims 15, 16, 25-28, and 35 under 35 USC 102(a)(1) have been fully considered and are persuasive. Therefore, the rejection has been withdrawn. However, upon further consideration, a new ground of rejection is made in view of the newly found prior art, Ahn, US 2024/0056575 A1, Stepin, US 2019/0313125, and view of Minnen, US 2020/0027247 A1.
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 15, 16, 25-28, and 35 are rejected under 35 U.S.C. 103 as being unpatentable over Schoers, in view of Ahn, US 2024/0056575 A1, in view of Stepin, US 2019/0313125 A1.
Regarding claim 15, Regarding claim 15, Schoers discloses: a method for image encoding, comprising:
obtaining a coded representation of an objective image (Step 452 in figure 4, “encoding a first compression input data of the series to a latent space representation of the first compression input data.”), the coded representation comprising values of a group of parameters of a latent representation of the objective image (See “latent values”), the group of parameters of the latent representation being produced with a trained machine-learning-based encoder (See [0028], disclosing that the invention uses a neural encoder/decoder with a pre-trained probability model which is then deployed to a compressed data receiver 126.);
determining an objective function associated with a decoder based on the coded representation (See rate-distortion objective function in equation 4.);
determining a group of adjustments of the values of the group of parameters of the latent representation based on a comparison between a group of change degrees of the objective function for the group of parameters of the latent representation and a threshold degree (See “Refine Latents” subroutine in figure 4, noting that this loop containing the objective function is looped until convergence, i.e., until change degree of objective function is below a threshold, causing convergence of latent representation y.);
adjusting at least some of the values of the group of parameters of the latent representation based on the group of adjustments so as to obtain an adjusted coded representation of the objective image (See “Refine Latents” step 454 in figure 4. This is an iterative step. See [0038].); and
obtaining an objective bitstream of the objective image based on the adjusted coded representation of the objective image (See “encode(x)” procedure in figure 3; arithmetic encoding (AE) step returns bitstream b from encoded, quantized latent representation y.).
Schoers does not disclose:
wherein the objective bitstream is encoded with at least one of:
first side information, which indicates a quantization parameter for quantizing the latent representation; and
However, transmitting quantization parameter values through a bitstream is disclosed in an analogous art by Ahn. See [0240], where Ahn discloses “dequantization may refer to scaling with a quantization step mapped to a quantization parameter transmitted through a bitstream”
Although not explicitly disclosed in Schoers, transmitting QP value information about a latent representation, as part of the compressed data bitstream 128 (Schoers [0014]) from encoder to decoder would have been obvious to one having ordinary skill in the art before the time of the applicant’s effective filing date, in order to efficiently coordinate between encoder and decoder. Incorporating QP information in a bitstream would have entailed simply combining the image encoding method disclosed in Schoers with a QP transmission, as disclosed in Ahn, without changing their respective functions, and the combination would have yielded nothing more than predictable results for one of ordinary skill in the art. KSR Int'l Co. v. Teleflex Inc. See 2143.1.A. 550 U.S. at 416, 82 USPQ2d at 1395.
The combination of Schoers in view of Ahn does not disclose:
second side information, which indicates a post-processing parameter for performing denoising as part of post-processing on a decoded image generated from the objective bitstream.
However, this limitation is disclosed in analogous art by Stepin. Stepin discloses in [0011] sending filter parameters from encoder to decoder side, and applying a filter as a post-filter (decoded picture improvement.
It would have been obvious to one having ordinary skill in the art before the time of the applicant’s effective filing date to incorporate the feature, disclosed in Stepin, of a denoising filter post-processing parameter transmitted through a bitstream, to improve the decoded video quality. Although Schoers does not disclose explicitly any kind of post-filtering, such tools were part of compression standards (H.264/AVC, H.265HEVC) known before the time of the applicant’s effective filing date, for this purpose, as disclosed in Stepin [0004].
Regarding claim 16, the combination of Schoers, in view of Ahn, in view of Stepin discloses the limitations of claim 15, upon which depends claim 16. This combination, specifically, Schoers, further discloses: the method of claim 15, wherein the determining the group of adjustments comprises:
in response to determining that a first change degree of the objective function with a first parameter, among the group of parameters, is less than or equal to the threshold degree, determining an adjustment of the first parameter to be zero (See figure 3 pseudocode. When the change degree of the objective function is below a threshold, the convergence condition for latent representation y is met and no further refinement to the latent representation is made, i.e. the adjustment of the latent representation is zero.).
Regarding claim 25, the combination of Schoers, in view of Ahn, in view of Stepin discloses the limitations of claim 15, upon which depends claim 25. This combination, specifically, Schoers, further discloses: the method of claim 15, further comprising:
iteratively repeating the determining the group of adjustments and the adjusting the at least some of the values of the group of parameters of the latent representation adjusting the coded representation until a convergence condition associated with the objective function is met (See “procedure REFINELATENTS(y, x)” in figure 3 which adjusts parameters of a latent representation y in a loop until the latent value, defined in part by objective function L, converges..).
Decoding method claims 26, and device claims 27, 28, and 35 correspond, respectively, to encoding method claim 15, in the case of claims 26 and 27, encoding method claims 16 and 25, in the case of claims 28 and 35, respectively, and are rejected for the same reasons of obviousness as given above.
Claim 21 is rejected under 35 U.S.C. 103 as being unpatentable over Schoers, in view of Ahn, in view of Stepin, in further view of Minnen, US 2020/0027247 A1.
Regarding claim 21, the combination of Schoers in view of Ahn in view of Stepin discloses the limitations of claim 15, upon which claim 21 depends. This combination does not disclose: the method of claim 15, wherein the coded representation further comprises values of parameters of a hyper representation a second coded representation, the second coded hyper representation being generated based on the first coded latent representation so as to indicate a distribution characteristic of the first coded latent representation, and wherein the method further comprises, while adjusting the at least some of the values of the group of parameters of the latent representation, adjusting at least some of the values of the parameters of the hyper representation.
However, Minnen discloses in an analogous art directed video compression using a neural network having conditional entropy models the following limitations:
the method of claim 15, wherein the coded representation further comprises values of parameters of a hyper representation a second coded representation (See [0005], which discloses ), the second coded hyper representation being generated based on the first coded latent representation so as to indicate a distribution characteristic of the first coded latent representation (See [0005], which discloses “An entropy encoded representation of the latent representation of the data is generated using the latent representation of the entropy model, including determining the probability distribution parameters defining the entropy model using the latent representation of the entropy model.”), and wherein the method further comprises, while adjusting the at least some of the values of the group of parameters of the latent representation, adjusting at least some of the values of the parameters of the hyper representation (Code symbols of a quantization of the latent representation of the data are autoregressively processed by one or more neural network layers to generate a set of context outputs. The context outputs and a quantization of the latent representation of the entropy model are processed by one or more neural network layers to generate the probability distribution parameter defining the entropy model.).
It would have been obvious to one having ordinary skill in the art before the time of the applicant’s effective filing date to incorporate the steps disclosed in Minnen for adjusting parameters of a latent representation of an entropy model, as disclosed in Minnen, in order to improve the compression efficiency by generating an improved, “richer” entropy model. See Minnen [0047]-[0048].
Allowable Subject Matter
Claims 17-19, 22-24, and 29-34 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 and any intervening claims.
The following is a statement of reasons for the indication of allowable subject matter:
Regarding claim 17, the prior art does not disclose or suggest: the method of claim 15, wherein the determining the group of adjustments comprises:
in response to determining that a given change degree of the objective function associated with a second given parameter, among the group of parameters, is larger than the threshold degree, determining an adjustment of the given parameter based on the given change degree so as to cause the adjustment of the given parameter to be proportional to the given change degree.
The closest prior art, Schoers, US 2020/0366914 A1 discloses a machine-learning-based encoder that uses an objective function to determine how to adjust parameters of a latent representation, as disclosed in “Refine Latents” subroutine in figure 4, noting that this loop containing the objective function is looped until convergence, i.e., until change degree of objective function is below a threshold, causing convergence of latent representation y. However, Schoers does not disclose determining an adjustment amount of an objective function’s parameter based on the objective function’s change amount being larger than a threshold so as to cause the objective function adjustment amount to be proportional to the change degree.
Regarding claim 18, the method of claim 17, wherein the determining the adjustment of the given parameter based on the second given change degree comprises:
determining a maximum change degree in the group of change degrees; and
determining the adjustment of the given parameter based on a ratio of the second given change degree to the maximum change degree so as to cause the adjustment of the given parameter to be proportional to the ratio.
Regarding claim 19, the method of claim 15, wherein the threshold degree is determined based on a product of a maximum change degree in the group of change degrees and a predetermined coefficient.
Regarding claim 22, the prior art does not disclose: the method of claim 21, wherein the coded representation comprises multiple partial coded representations corresponding to multiple locations in the objective image, and wherein obtaining the objective bitstream comprises, with respect to a given location among the multiple locations:
determining a first entropy encoding parameter for indicating a mean value based on the hyper representation, the first entropy encoding parameter being irrelevant to a contextual parameter, the contextual parameter being used to indicate a coded representation of a group of associated locations associated with a given location among the multiple locations; and
generating a partial bitstream corresponding to the given location in the objective bitstream based at least in part on the first entropy encoding parameter.
Regarding claim 24, the method of claim 15, wherein the objective bitstream is encoded with at least one of:
first side information, which indicates a quantization parameter for quantizing the latent representation; and
second side information, which indicates a post-processing parameter for performing post-processing on a decoded image generated from the objective bitstream
Claims 29-34 are objected to as containing allowable subject matter for the same reasons as 17-24, respectively.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to KYLE M LOTFI whose telephone number is (571)272-8762. The examiner can normally be reached 9:00-5:00.
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, Brian Pendleton can be reached at 571-272-7527. 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.
/KYLE M LOTFI/Examiner, Art Unit 2425
Prosecution Insights