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 .
Summary
2. This office action for US Patent application 18/778,818 is responsive to communications filed on 11/26/2025, in response to the Non-Final Rejection of 08/22/2025. Currently, claims 1-20 are pending and are presented for examination.
Response to Arguments
3. The information disclosure statement (IDS) was submitted on 01/30/2026. The submission is in compliance with the provisions of 37 CFR § 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
4. Applicant's Remarks see pages 6-8, with respect to the amendment and argument have been fully considered, but they are not persuasive.
Applicant urges that Zhu does not explicitly disclose “determining
a first part of a first sample of a reconstructed latent representation of the visual data, the first part indicating a prediction of the first sample" and "determining a second part of the first sample, the second part indicating a difference between the first sample and the first part" as cited in claim 1 (see page 6-7: Applicant’s remarks). The examiner explicitly disagrees. Zhu fairly discloses an encoder sub-network having a series of transformer layers to perform a non-linear transform that converts an input image into a latent representation. each encoder transformer layer can include a set of consecutively arranged shifted window transformer blocks, respectively (also referred to herein as “encoder transformer block sets” or “transformer block sets”) (see paragraph 0117; Figs. 5A and 5B). Zhu further teaches prediction blocks, inter/intra prediction to generate a prediction of samples (e.g., first and second samples as claimed) in paragraphs 0086, 0088 and the prediction unit or prediction block is then subtracted from the original video data to get residuals (see paragraph 0090; also see cited prior art portions in claims 16 and 17). Moreover, these features are merely the steps and parts of conventional encoding and decoding in technical fields.
The Applicants also contend that “Zhu is silent about what does such as a subportion(s) indicate” (see page 6: Applicants’ Remark). However, claim 1 does not recite “subportion or sub-portion in the claim(s). Although the claims are interpreted in light of the specification, limitations from the specification are not read into the claims. See In re Van Geuns, 988 F.2d 1181, 26 USPQ2d 1057 (Fed. Cir. 1993).
Claim Rejections - 35 USC § 102
5. 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 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.
6. 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 –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(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.
7. Claims 1- 20 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Zhu et al. (US 2023/0100413A1) (hereinafter Zhu).
Regarding claim 1, Zhu discloses a method for visual data processing (e.g., see abstract; Figs. 1-6B), comprising:
determining, during a conversion between visual data and a bitstream of the visual data with a neural network (NN)-based model (e.g., see Figs. 2A-2B: paragraphs 0081, 0082: neural network base model/architectures; Fig. 4, paragraphs 0111-0114; also see Figs. 3, 5a-6B), a first part of a first sample of a reconstructed latent representation of the visual data, the first part indicating a prediction of the first sample (e.g., see abstract, paragraphs 0004, 0035, 0069: latent representation and sub-portion of input data; Figs. 5a-5b, paragraphs 0070, 0117-0119: latent representation 555a, 555b and converting the latent presentation into a reconstructed image);
determining a second part of the first sample, the second part indicating a difference between the first sample and the first part (e.g., see Figs. 5A-5B, paragraphs 0117-0120: stage or parts 520-550); and
performing the conversion based on the second part (e.g., see Figs. 5A-5B, paragraphs 0117-0120: stage or parts 520-550 and converting the latent presentation into a reconstructed image; paragraph 0070: conversion; also see Figs. 4, 6A-6B).
Regarding claim 2, Zhu discloses the method of claim 1, wherein determining the first part comprises: determining the first part based on a set of already reconstructed samples of the reconstructed latent representation (e.g., Figs. 5a-5b, paragraphs 0070, 0117-0119: converting the latent presentation into a reconstructed image).
Regarding claim 3, Zhu discloses the method of claim 2, wherein determining the first part based on the set of already reconstructed samples comprises: generating intermediate information based on the set of already reconstructed samples (e.g., see paragraphs 0063, 0103, 0104: intermediate input/information) by using a first subnetwork in the NN-based model (e.g., see abstract, paragraphs 0007, 0070-0072: sub-network; also see Figs. 4-6B: sub-network); and generating the first part based on the intermediate information by a second subnetwork in the NN-based model (e.g., see abstract, paragraphs 0007, 0070-0072: sub-network; also see Figs. 4-6B: sub-network).
Regarding claim 4, Zhu discloses the method of claim 1, wherein a process for determining samples of the reconstructed latent representation is autoregressive (e.g., see paragraphs 0066, 0067, 0070, 0111: autoregressive; also see Figs. 4-6B).
Regarding claim 5, Zhu discloses the method of claim 4, wherein the process is implemented with a multistage context model (e.g., see paragraphs 0066, 0069, 0094: context of image/video coding; also see Figs. 6A-7A, paragraphs 0130, 0139, 0145).
Regarding claim 6, Zhu discloses the method of claim 3, wherein generating the first part comprises: generating first hyper information based on a first quantized hyper latent representation (e.g., see Fig. 4, paragraphs 0011, 00112: hyperprior model; Figs. 5a-5b, paragraphs 0070, 0117-0119: latent representation) by using a third subnetwork in the NN-based model (e.g., see abstract, paragraphs 0007, 0070-0072: sub-network; also see Figs. 4-6B: sub-network); and generating the first part based on the intermediate information and the first hyper information (e.g., see Fig. 4, paragraphs 0011, 00112: hyperprior model) by using the second subnetwork (e.g., see abstract, paragraphs 0007, 0070-0072: sub-network; also see Figs. 4-6B: sub-network).
Regarding claim 7, Zhu discloses the method of claim 1, wherein determining the first part comprises: determining the first part based on a first quantized hyper latent representation (e.g., see Fig. 4, paragraphs 0011, 00112: hyperprior model).
Regarding claim 8, Zhu discloses the method of claim 7, wherein determining the first part based on the first quantized hyper latent representation (e.g., see Fig. 4, paragraphs 0011, 00112: hyperprior model) comprises: processing the first quantized hyper latent representation (e.g., see Fig. 4, paragraphs 0011, 00112: hyperprior model) by using a third subnetwork in the NN-based model (e.g., see abstract, paragraphs 0007, 0070-0072: sub-network; also see Figs. 4-6B: sub-network).
Regarding claim 9, Zhu discloses the method of claim 6, wherein the third subnetwork is a hyper decoder subnetwork (e.g., see abstract, paragraphs 0007, 0070-0072: sub-network; Fig. 4, paragraphs 0011, 00112: hyperprior model; also see Figs. 5a-6B: sub-network).
Regarding claim 10, Zhu discloses the method of claim 6, wherein the first quantized hyper latent representation is determined based on the bitstream, or wherein the first hyper information comprises prediction information (e.g., see Fig. 4, paragraphs 0011, 00112: hyperprior model).
Regarding claim 11, Zhu discloses the method of claim 1, wherein determining the second part comprises: generating second hyper information based on a second quantized hyper latent representation by using a fifth subnetwork in the NN-based model (e.g., see abstract, paragraphs 0007, 0070-0072: sub-network; also see Figs. 4-6B: sub-network; paragraphs 0011, 00112: hyperprior model), the second quantized hyper latent representation (e.g., see Fig. 4, paragraphs 0011, 00112: hyperprior model) being determined based on a first portion of the bitstream (e.g., see abstract, paragraphs 0007, 0070-0072: sub-network; also see Figs. 4-6B: sub-network); and obtaining the second part by performing an entropy decoding process on a second portion of the bitstream based on the second hyper information representation (e.g., see Fig. 4, paragraphs 0011, 00112: hyperprior model), the second portion being different from the first portion (e.g., see abstract, paragraphs 0004, 0035, 0069: latent representation and sub-portion of input data; Figs. 5a-5b, paragraphs 0070, 0117-0119).
Regarding claim 12, Zhu discloses the method of claim 11, wherein the second hyper information comprises a variance, or wherein the fifth subnetwork is a hyper scale decoder subnetwork (e.g., see abstract, paragraphs 0007, 0070-0072: sub-network; also see Figs. 4-6B: sub-network), or wherein the entropy decoding process is an arithmetic decoding process, or wherein the second quantized hyper latent representation is the same as the first quantized hyper latent representation (e.g., see abstract, paragraphs 0007, 0070-0072: sub-network; also see Figs. 4-6B: sub-network; paragraphs 0011, 00112: hyperprior model).
Regarding claim 13, Zhu discloses the method of claim 1, wherein performing the conversion comprises: determining the first sample based on the first part and the second part (e.g., see abstract, paragraphs 0004, 0035, 0069: latent representation and sub-portion of input data; Figs. 5a-5b, paragraphs 0070, 0117-0119: latent representation 555a, 555b and converting the latent presentation into a reconstructed image); and performing the conversion based on a synthesis transform on the first sample (e.g., see Figs. 5a-5b, paragraphs 0070, 0117-0119: latent representation 555a, 555b and converting the latent presentation into a reconstructed image).
Regarding claim 14, Zhu discloses the method of claim 13, wherein the first sample is determined based on a sum of the first part and the second part (e.g., see abstract, paragraphs 0004, 0035, 0063, 0069: latent representation and sub-portion of input data; Figs. 5a-5b, paragraphs 0070, 0117-0119.
Regarding claim 15, Zhu discloses the method of claim 1, wherein the first part is the prediction of the first sample, or the second part is a quantized residual of the first sample, or wherein the reconstructed latent representation is a quantized latent representation of the visual data (e.g., see Figs. 5a-5b, paragraphs 0070, 0117-0119: latent representation 555a, 555b and converting the latent presentation into a reconstructed image), or wherein the visual data comprise a picture of a video or an image (e.g., see paragraphs 0038, 0039: video or image data; also see Figs. 3-7B).
Regarding claim 16, Zhu discloses the method of claim 1, wherein the conversion includes encoding the visual data into the bitstream (e.g., see paragraphs 0087, 0088, 0095: bitstream; Fig. 3, paragraph 0098).
Regarding claim 17, Zhu discloses the method of claim 1, wherein the conversion includes decoding the visual data from the bitstream (e.g., see paragraphs 0087, 0088, 0095: bitstream; Fig. 3, paragraph 0098).
Regarding claim 18, this claim is an apparatus claim of a method version as applied to claim 1 above, wherein the apparatus performs the same limitations cited in claim 1, the rejections of which are incorporated herein. Furthermore, Zhu discloses the apparatus for image processing (see Figs. 1, 3, 5a-5b, 10).
Regarding claim 19, this claim is a non-transitory computer-readable storage medium claim of a method version as applied to claim 1 above, wherein the non-transitory computer-readable storage medium performs the same limitations cited in claim 1, the rejections of which are incorporated herein. Furthermore, Zhu discloses the non-transitory computer-readable storage medium (see Figs. 1, 3, 5a-5b, 10; paragraphs 0097, 0099).
Regarding claim 20, this claim is a non-transitory computer-readable storage medium claim of a method version as applied to claim 1 above, wherein the non-transitory computer-readable storage medium performs the same limitations cited in claim 1, the rejections of which are incorporated herein. Furthermore, Zhu discloses the non-transitory computer-readable storage medium (see Figs. 1, 3, 5a-5b, 10; paragraphs 0097, 0099)
Conclusion
8. 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 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 extension fee 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.
9. Any inquiry concerning this communication or earlier communications from the examiner should be directed to ON MUNG whose telephone number is (571) 270-7557 and whose direct fax number is (571) 270-8557. The examiner can normally be reached on Mon-Fri 9am - 6pm (ET).
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, JAMIE ATALA can be reached on (571)272-7384. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/ON S MUNG/Primary Examiner, Art Unit 2486