Prosecution Insights
Last updated: April 19, 2026
Application No. 18/442,622

METHODS FOR COMPLEXITY REDUCTION OF NEURAL NETWORK BASED VIDEO CODING TOOLS

Non-Final OA §103
Filed
Feb 15, 2024
Examiner
KWAN, MATTHEW K
Art Unit
2482
Tech Center
2400 — Computer Networks
Assignee
Qualcomm Incorporated
OA Round
2 (Non-Final)
70%
Grant Probability
Favorable
2-3
OA Rounds
2y 10m
To Grant
99%
With Interview

Examiner Intelligence

Grants 70% — above average
70%
Career Allow Rate
250 granted / 359 resolved
+11.6% vs TC avg
Strong +35% interview lift
Without
With
+34.7%
Interview Lift
resolved cases with interview
Typical timeline
2y 10m
Avg Prosecution
24 currently pending
Career history
383
Total Applications
across all art units

Statute-Specific Performance

§101
3.7%
-36.3% vs TC avg
§103
58.5%
+18.5% vs TC avg
§102
14.2%
-25.8% vs TC avg
§112
11.6%
-28.4% vs TC avg
Black line = Tech Center average estimate • Based on career data from 359 resolved cases

Office Action

§103
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. 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. Claim(s) 1-2, 5-8, 9, 11-12, 15-18 and 19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Ma et al. (U.S. 2022/0007015), hereinafter Ma in view of Wang et al. ("EE1-1.2: Neural Network Based In-loop Filter with a Single Model", JVET-Z0091, 20-29 April 2022, hereinafter Wang and further in view of Park et al. (U.S. 2020/0120340), hereinafter Park. Wang was cited in the Applicant’s IDS dated 5/22/24. Regarding claims 1 and 11, Ma discloses an apparatus configured to code video data, the apparatus comprising: a memory configured to store a picture of video data (Ma [0031] and [0171]); and processing circuitry in communication with the memory (Ma [0171]), the processing circuitry configured to: receive the picture of video data (Ma fig. 1, #106); reconstruct a block of the picture of video data to generate a reconstructed block (Ma [0030]); and perform a neural network (NN)-based filter process on the reconstructed block to generate a filtered block (Ma [0037]), the NN-based filter process using reconstruction samples of the block, prediction samples of the block, and supplementary data related to the block as inputs (Ma [0037], figs. 1 and 2). Ma does not explicitly disclose wherein the NN-based filter process includes an initial processing of one or more types of the supplementary data with fewer computations relative to the initial processing of the reconstruction samples and the prediction samples. However, Wang teaches receiving a picture of video data (Wang p. 2, fig. 2) and wherein the NN-based filter process includes an initial processing of one or more types of the supplementary data with fewer computations relative to the initial processing of the reconstruction samples and the prediction samples (Wang fig. 2). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Ma’s method with the missing limitations as taught by Wang to provide a neural network filter with constrained memory size and lower complexity to achieve a good trade-off between performance and complexity (Wang p. 6, section 4). As shown above, all of the limitations are known, they can be applied to a known device such as a processor to yield a predictable result of creating a less complex neural network filtering system. Ma does not explicitly disclose wherein the initial processing of the one or more types of the supplementary data includes a 1x1 convolution. However, Park teaches wherein the initial processing of the one or more types of the supplementary data includes a 1x1 convolution (Park [0162] and fig. 6B). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method taught by Ma in view of Wang with the missing limitations as taught by Park to maintain the initial information and have a smaller error (Park [0162]). Regarding claims 2 and 12, Ma in view of Wang and Park teaches the method and apparatus of claims 1 and 11, wherein the initial processing of the reconstruction samples and the prediction samples includes a 3x3 convolution, and wherein the initial processing of the one or more types of the supplementary data includes fewer computations than the 3x3 convolution (Wang p. 2, fig. 2). The same motivation for claim 1 applies to claims 2 and 12. Regarding claims 5 and 15, Ma in view of Wang and Park teaches the method and apparatus of claims 1 and 11, wherein the one or more types of the supplementary data include one or more of a quantization parameter (QP), partitioning information, coding mode identification, or a boundary strength (BS) for a deblocking filter (Wang fig. 2). The same motivation for claim 1 applies to claims 5 and 15. Regarding claims 6 and 16, Ma in view of Wang and Park teaches the method and apparatus of claims 1 and 11. Ma does not explicitly disclose wherein the initial processing of the one or more types of the supplementary data includes performing a feature map derivation for a first type of the supplementary data that has a static value for the block. However, Park further teaches, wherein the initial processing of the one or more types of the supplementary data includes performing a feature map derivation for a first type of the supplementary data that has a static value for the block (Park [0158], [0162] and fig. 6B). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method taught by Ma in view of Wang and Park with the missing limitations as taught by Park to maintain the initial information and have a smaller error (Park [0162]). Regarding claims 7 and 17, Ma in view of Wang and Park teaches the method and apparatus of claims 6 and 16, wherein the feature map derivation includes a single 1x1 convolution and a value replication process (Park [0162] and fig. 6B). The same motivation for claim 6 applies to claims 7 and 17. Regarding claims 8 and 18, Ma in view of Wang and Park teaches the method and apparatus of claims 1 and 11, wherein the initial processing of the one or more types of the supplementary data includes performing a replication of a value of a first type of the supplementary data that has a static value for the block without performing a convolution on the first type of the supplementary data (Park [0162] and fig. 6B). The same motivation for claim 6 applies to claims 8 and 18. Regarding claims 9 and 19, Ma in view of Wang and Park teaches the method and apparatus of claims 1 and 11, wherein the apparatus is configured to decode video data and wherein the apparatus further comprises: use a decoded picture that includes the filtered block as reference for prediction in other encoded pictures (Ma [0030], figs. 1 and 2). Claim(s) 3 and 13 is/are rejected under 35 U.S.C. 103 as being unpatentable over Ma in view of Wang and Park as applied to claims 1 and 11 above, and further in view of Nash et al. (U.S. 2024/0104785), hereinafter Nash. Regarding claims 3 and 13, Ma in view of Wang and Park teaches the method and apparatus of claims 1 and 11. Ma does not explicitly disclose wherein the one or more types of the supplementary data have a sparse representation relative to the reconstruction samples and the prediction samples. However, Nash teaches, wherein the one or more types of the supplementary data have a sparse representation relative to the reconstruction samples and the prediction samples (Nash [0064]). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method taught by Ma in view of Wang and Park with the missing limitations as taught by Nash to significantly reduce the time, memory and computational costs required to generate synthetic images (Nash [0037]). Claim(s) 10 and 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Ma in view of Wang and Park as applied to claims 1 and 11 above, and further in view of Ding et al. (U.S. 2022/0385896), hereinafter Ding. Regarding claims 10 and 20, Ma in view of Wang and Park teaches the method and apparatus of claims 1 and 11, wherein the apparatus is configured to encode video data (Ma [0030] and fig. 1). Ma does not explicitly disclose wherein the apparatus further comprises: a camera configured to capture the picture of video data. However, Ding teaches wherein the apparatus further comprises: a camera configured to capture the picture of video data (Ding [0071]). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method taught by Ma in view of Wang and Park with the missing limitations as taught by Ding to create a stream of uncompressed images for video coding (Ding [0071]). Response to Arguments Applicant’s arguments, see pgs. 6-9 of Applicant’s Remarks, filed 1/7/26, with respect to the rejection(s) of claim(s) 1 and 11 under 35 U.S.C. § 103 have been fully considered and are persuasive. Therefore, the rejection has been withdrawn. However, upon further consideration, a new ground(s) of rejection is made in view of newly cited section of Park, which was cited for dependent claims 6-8 and 16-18 previously. Conclusion Any inquiry concerning this communication or earlier communications from the examiner should be directed to MATTHEW KWAN whose telephone number is (571)270-7073. The examiner can normally be reached Monday-Friday 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, Chris Kelley can be reached at (571)272-7331. 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. /MATTHEW K KWAN/Primary Examiner, Art Unit 2482
Read full office action

Prosecution Timeline

Feb 15, 2024
Application Filed
Oct 07, 2025
Non-Final Rejection — §103
Jan 07, 2026
Response Filed
Jan 27, 2026
Non-Final Rejection — §103 (current)

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12603980
SEAMLESS TRANSITIONS IN LARGE-SCALE VIDEO
2y 5m to grant Granted Apr 14, 2026
Patent 12587681
POINT CLOUD DATA FRAMES COMPRESSION
2y 5m to grant Granted Mar 24, 2026
Patent 12574540
METHODS AND APPARATUS OF VIDEO CODING FOR TRIANGLE PREDICTION
2y 5m to grant Granted Mar 10, 2026
Patent 12574548
METHOD AND APPARATUS FOR ENCODING/DECODING VIDEO, AND RECORDING MEDIUM STORING BIT STREAM
2y 5m to grant Granted Mar 10, 2026
Patent 12574530
TEMPLATE AVAILABILITY FOR TEMPLATE MATCHING TOOLS
2y 5m to grant Granted Mar 10, 2026
Study what changed to get past this examiner. Based on 5 most recent grants.

AI Strategy Recommendation

Get an AI-powered prosecution strategy using examiner precedents, rejection analysis, and claim mapping.
Powered by AI — typically takes 5-10 seconds

Prosecution Projections

2-3
Expected OA Rounds
70%
Grant Probability
99%
With Interview (+34.7%)
2y 10m
Median Time to Grant
Moderate
PTA Risk
Based on 359 resolved cases by this examiner. Grant probability derived from career allow rate.

Sign in with your work email

Enter your email to receive a magic link. No password needed.

Personal email addresses (Gmail, Yahoo, etc.) are not accepted.

Free tier: 3 strategy analyses per month