Prosecution Insights
Last updated: April 19, 2026
Application No. 18/625,535

VIDEO DENOISING USING RECURRENT NEURAL NETWORK WITH GATED RECURRENT UNIT

Non-Final OA §102§103
Filed
Apr 03, 2024
Examiner
NGUYEN, LEON VIET Q
Art Unit
2663
Tech Center
2600 — Communications
Assignee
Visionary AI Vision Ltd.
OA Round
1 (Non-Final)
85%
Grant Probability
Favorable
1-2
OA Rounds
2y 8m
To Grant
95%
With Interview

Examiner Intelligence

Grants 85% — above average
85%
Career Allow Rate
954 granted / 1122 resolved
+23.0% vs TC avg
Moderate +10% lift
Without
With
+10.2%
Interview Lift
resolved cases with interview
Typical timeline
2y 8m
Avg Prosecution
26 currently pending
Career history
1148
Total Applications
across all art units

Statute-Specific Performance

§101
4.9%
-35.1% vs TC avg
§103
61.5%
+21.5% vs TC avg
§102
17.9%
-22.1% vs TC avg
§112
10.4%
-29.6% vs TC avg
Black line = Tech Center average estimate • Based on career data from 1122 resolved cases

Office Action

§102 §103
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 . Information Disclosure Statement The information disclosure statement (IDS) submitted on 4/3/2024 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner. Claim Rejections - 35 USC § 102 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 (i.e., changing from AIA to pre-AIA ) 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. 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. Claim(s) 1, 4, and 5 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Guo et al ("Gated recurrent unit for video denoising." arXiv preprint arXiv:2210.09135, (10/17/2022), pages 1-5, retrieved from the Internet on 2/12/2026). Regarding claim 1, Guo discloses a method of denoising a video, comprising: capturing a plurality of frames of the video (fig. 1(a), input noisy frame; section IV.C, “We test the proposed GRU-VD network on a video captured under low-light conditions”); inputting raw data from the frames into a recurrent neural network, said recurrent neural network including a gated recurrent unit (section III.B, GRU is a kind of RNNs with gating mechanisms…The current input frame xn); outputting a first denoised frame from the recurrent neural network (Final denoised output of current frame in fig. 3) while maintaining vectors corresponding to the first denoised frame in a memory of the recurrent neural network (section I, the update gate recursively fuses the initial denoising result with previous frame output to further improve accuracy; section III.C, The relevant content from previous frame output can assist spatial denoising of the current frame. This implies that a feature or vector is maintained in proceeding steps); and for each subsequent frame of the video (current input on the right side of fig. 2), inputting raw data from the frame and the vectors from the memory into the recurrent neural network (right side of fig. 2, the previous output is interpreted to have the vectors from memory; section III.C, The relevant content from previous frame output can assist spatial denoising of the current frame), while applying the gated recurrent unit in order to selectively remove vectors from consideration of the neural network (Reset gate and Update gate in fig. 2; section II.B, There is a reset gate r to identify the useful content of yn-1, a hidden activation s as preprocessing to get a candidate, and an update gate f to estimate the final fusion output. It is known that the update gate and reset gate are two vectors that decide which information will get passed on to the output (see para. [0002] of applicant’s specification)), and outputting subsequent denoised frames from the recurrent neural network (Current output in fig. 2), while storing vectors from the denoised frame in the memory (section III.C, The relevant content from previous frame output can assist spatial denoising of the current frame. This would require storing the features from the denoised frame to be used in subsequent iterations). Regarding claim 4, Guo discloses a method further comprising performing the denoising as part of an image signal processing pipeline (section I, For this reason, denoising is an essential step in image signal processing (ISP) to enhance quality). Regarding claim 5, the claim recites similar subject matter a claim 1 and is rejected for the same reasons as stated above. Claim Rejections - 35 USC § 103 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 (i.e., changing from AIA to pre-AIA ) 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. 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. Claim(s) 2 is/are rejected under 35 U.S.C. 103 as being unpatentable over Guo et al ("Gated recurrent unit for video denoising." arXiv preprint arXiv:2210.09135, (10/17/2022), pages 1-5, retrieved from the Internet on 2/12/2026) in view of Liu et al (US20240095880). Regarding claim 2, Guo fails to teach a method further comprising outputting the denoised frames as a video at a rate of at least 10 frames per second. However Liu teaches outputting denoised frames (610 in fig. 6) as a video at a rate of at least 10 frames per second (para. [0559], In at least one embodiment, output frames are generated at a target rate at or over 20 frames per second (fps) including or not limited to 23.976 fps, 24 fps, 25 fps, 29.97 fps, 30 fps, 48 fps, 50 fps, 59.94 fps, 60 fps, 90 fps, 120 fps, 240 fps, and any other suitable target frame rate). Therefore taking the combined teachings of Guo and Liu as a whole, it would have been obvious to one of ordinary skill in the art at the time the invention was filed to incorporate the steps of Liu into the method of Guo. The motivation to combine Liu and Guo would be to generate output frames at a rate which can be perceived as continuous motion for a human being with minimal latency (para. [0059] of Liu). Claim(s) 3 is/are rejected under 35 U.S.C. 103 as being unpatentable over Guo et al ("Gated recurrent unit for video denoising." arXiv preprint arXiv:2210.09135, (10/17/2022), pages 1-5, retrieved from the Internet on 2/12/2026) in view of Mihal et al (US11151695). Regarding claim 3, Guo fails to explicitly teach a method wherein the recurrent neural network considers both spatial patterns in the frames and temporal continuity between adjacent frames. However Mihal teaches where a recurrent neural network (col. 4 lines 49-51) considers both spatial patterns (col. 4 lines 49-51) in the frames (col. 19 lines 25-29) and temporal continuity between adjacent frames (col. 4 line 63 - col. 5 line 3). Therefore taking the combined teachings of Guo and Mihal as a whole, it would have been obvious to one of ordinary skill in the art at the time the invention was filed to incorporate the steps of Mihal into the method of Guo. The motivation to combine Mihal and Guo would be to improve accuracy of object detection and tracking in real world scenarios (col. 22 lines 27-30 of Mihal). Related Art Ryder et al (US20240214578) – see para. [0129]-[0130] Conclusion Any inquiry concerning this communication or earlier communications from the examiner should be directed to LEON VIET Q NGUYEN whose telephone number is (571)270-1185. The examiner can normally be reached Mon-Fri 11AM-7PM. 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, Gregory Morse can be reached at 571-272-3838. 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. /LEON VIET Q NGUYEN/Primary Examiner, Art Unit 2663
Read full office action

Prosecution Timeline

Apr 03, 2024
Application Filed
Mar 12, 2026
Non-Final Rejection — §102, §103 (current)

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12602795
FALSE POSITIVE REDUCTION OF LOCATION SPECIFIC EVENT CLASSIFICATION
2y 5m to grant Granted Apr 14, 2026
Patent 12597270
SYSTEMS AND METHODS FOR USING IMAGE DATA TO ANALYZE AN IMAGE
2y 5m to grant Granted Apr 07, 2026
Patent 12592094
METHODS AND SYSTEMS OF AUTOMATICALLY ASSOCIATING TEXT AND CONTROL OBJECTS
2y 5m to grant Granted Mar 31, 2026
Patent 12586235
SYSTEMS AND METHODS FOR HEAD RELATED TRANSFER FUNCTION PERSONALIZATION
2y 5m to grant Granted Mar 24, 2026
Patent 12586357
COLLECTING METHOD FOR TRAINING DATA
2y 5m to grant Granted Mar 24, 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

1-2
Expected OA Rounds
85%
Grant Probability
95%
With Interview (+10.2%)
2y 8m
Median Time to Grant
Low
PTA Risk
Based on 1122 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