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 .
DETAILED ACTION
This communication is a non-Final office action in merits. Claims 1-20 are presently pending and have been elected and considered below.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 6/24/2024 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Restriction Requirement
Applicant’s argument with respect to the restriction requirement has been considered. Restriction requirement is withdrawn.
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 of this title, 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 set forth in Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966), that are applied 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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1-2, 13, 17 are rejected under 35 U.S.C. 103 as being unpatentable over US 2022/0230282 A1, Zhang et al. (hereinafter Zhang).
As to claim 1, Zhang discloses a method for video processing, comprising:
receiving an input image (Figs 8, 54; pars 0106-0107);
extracting shallow features of the input image through a head network (Figs 21, 27-28, perform feature extraction on the image to be processed; pars 0007-0008, 0011, 0013, 0112, 0121, performing feature extraction including shallow features);
determining, based on the shallow features, residual features of the input image and enhancing a portion of the residual features by two or more weakly-connected-dense-attention-blocks (WCDABs) (Figs 38, 0041; pars 0300, 0309, 0314-0315, deblurring performance being improved upon adaptive multi-scale residual group operations on residual features; figs 0038, 0041, 0043, 44A-44B; pars 0121, 0309-0312, 0316, 0318-0319, the residual module contains two convolution operations and muti-scale feature map attention operations);
reconstructing the residual features to form a residual map (Figs 37, 0043; pars 0299-0300, 0308-0309, 0318, 0322, 0332, residual features being recovered or reconstructed); and
adding the residual map to the input image to generate a reconstructed image (Figs 22-23, 51; pars 00008, 0168, 0180-0184, 0199, 231, 0233, fused feature image after addition).
As to claim 2, Zhang discloses the method of claim 1, wherein the WCDAB includes two or more residual attention blocks (RABs) (Fig 43; pars 0316).
As to claim 13, Zhang discloses the method of claim 1, wherein the WCDAB includes a CSAB module configured to enhance the portion of the residual features (Figs 38, 41, multi-scale residual group module adapted with multi-scale feature map attention module to enhance the residual features; pars 0314, 0318-0319), and wherein the CSAB module includes a channel-attention-block (CAB) branch and a spatial attention block (SAB) branch (Figs 38, 41, 43, 44A).
As to claim 17, it is a system claim encompassed claim 1, rejection of claim 1 is therefore incorporated herein.
Claims 3-12, 14-16, 18-20 are rejected under 35 U.S.C. 103 as being unpatentable over Zhang in view of US 2018/0137406 A1, Howard et al. (hereinafter Howard) and further in view of CN 114266709, Li et al. see google translation for citation (hereinafter Li).
As to claim 3, Zhang discloses the method of claim 2, but does not expressly disclose a dual-branch structure, wherein convolutional layers of the dual-branch structure are depth-wise separable convolutional layers, and wherein the depth-wise separable convolutional layer includes a depth-wise part and a point-wise part.
Howard, in the same or similar field of endeavor further teaches convolutional neural network structure where convolutional layers are depth-wise separable convolutional layers, and wherein the depth-wise separable convolutional layer includes a depth-wise part and a point-wise part (Figs 4-A-4B, 5; pars 0010, 0019-0020, 0027-0031, 0072, 0085, convolutional layers of the dual-branch structure with depth-wise separable convolutional and a point-wise convolution layers).
Li, in the same or similar field of endeavor, additional teaches a dual branch parallel structure of a neural network system with separable convolution layers (Abstract; Fig 1).
Therefore, consider Zhang, Howard, and Li’s teachings as a whole, it would have been obvious to one of skill in the art before the filing date of invention to incorporate Howard and Li’s teachings in Zhang’s method to utilize parallel neural network structure with separable depth-wise and point-wise convolutional layers for reducing computational burden.
As to claim 4, Zhang as modified discloses the method of claim 3, wherein the dual-branch structure includes a first branch and a second branch, wherein the first branch includes a first convolutional layer with a first dimension (Howard: Fig 5; pars 0030, 0098, depthwise convolution layer with dimension of 3x3), and wherein the second branch includes two second convolutional layers with a second dimension (Howard: Fig 5; pars 0028, 0030, pointwise convolutional layer dimension being 1x1; Li: claim 1; Figs 1, 3).
As to claim 5, Zhang as modified discloses the method of claim 4, wherein the first dimension is the same as the second dimension (Zhang: Fig 32; pars 0011, 0016, 0209-0210, dimension is adjustable to be the same for fusing; Li: claim 1).
As to claim 6, Zhang as modified discloses the method of claim 5, wherein the first dimension is three by three (3x3) (see rejection in claim 4).
As to claim 7, Zhang as modified discloses the method of claim 4, wherein the first convolutional layer with the first dimension corresponds to a first receptive field, and wherein the two second convolutional layers correspond a second receptive field (Zhang: Fig 31; pars 0060, 0121, 0172, 0178, 0197, different receptive fields corresponding to their associated convolutional layers).
As to claim 8, Zhang as modified discloses the method of claim 7, wherein the second receptive field is greater than the first receptive field (Zhang: pars 0121, 0197, 0240).
As to claim 9, Zhang as modified discloses the method of claim 7, wherein the first receptive field is a three-by-three (3x3) field (Zhang: Fig 30; par 0241), and wherein second receptive field is a five-by-five (5x5) field (Zhang: pars 0241, 0243, note although Zhang gives example for the receptive field being 7x7 or 15x15, it indicates different receptive field such as 5x5 can be obtained via convolution/kennel structure as a design choice).
As to claim 10, Zhang as modified discloses the method of claim 7, wherein the RAB is configured to perform a channel shuffling operation to integrate features from the first receptive field and the second receptive field (Zhang: pars 0199, 0209-0210, 0230, 0249, 0252, fusing features from different features obtained from convolutional outputs through channel resizing).
As to claim 11, Zhang as modified discloses the method of claim 10, wherein the RAB is configured to form a common convolution layer after the channel shuffling operation, wherein the common convolution layer is configured to perform a channel dimensionality reduction operation so as to form a feature map (Zhang: pars 0011, 0201-0203, 0249, 0252, channel dimension reduction).
As to claim 12, Zhang as modified discloses the method of claim 11, wherein the RAB includes a channel attention block (CAB) module configured to emphasize channels in the feature map (Zhang: Fig 39; par 0312; Li: Abstract; Fig 1).
As to claim 14, Zhang as modified discloses the method of claim 13, wherein the CAB branch is configured to process an input feature from two or more RABs of the WCDAB to form a channel attention map (Zhang: Figs 38, 43; pars 0309-0310, 0312, 0316, 0319, channel attention process providing a channel attention map); the SAB branch is configured to process the input feature to form a spatial attention map (Li: Figs 1, 3; claim 1; page 2, par 5; page 4; par 1-8; page 7, pars 1, 10, providing a spatial attention module to generate a spatial attention map).
As to claim 15, Zhang as modified discloses the method of claim 14, further comprising merging the channel attention map and the spatial attention map to form a channel-spatial joint attention map (Li: Abstract; Fig 1, spatial attention branch with spatial attention module and channel attention branch with channel attention module generating individual attention features being fused for a joint attention map).
As to claim 16, Zhang as modified discloses the method of claim 13, wherein the SAB branch includes two parallel convolution layers of different sizes to convolve an input feature (Zhang: Figs 28-29, 0036, 38).
As to claim 18, it is rejected with the same reason as set forth in claim 4.
As to claim 19, it essentially recites a variation including functions and features recited in claims 1-4, and 13. Rejection of claims 1-4, and 13 are therefore incorporated herein.
As to claim 20, it is rejected with the same reason as set forth in claims 14-15.
Examiner’s Note
Examiner has cited particular column, line number, paragraphs and/or figure(s) in the reference(s) as applied to the claims for the convenience of the Applicant. Although the specified citations are representative of the teachings of the art and are applied to the specific limitations within the individual claim, other passages and figures may apply as well. It is respectfully requested from the applicant in preparing responses, to fully consider the reference(s) in entirety as potentially teaching all or part of the claimed invention, as well as the context of the passage as taught by the prior art or disclosed by the Examiner.
Contact Information
Any inquiry concerning this communication or earlier communications from the examiner should be directed to QUN SHEN whose telephone number is (571)270-7927. The examiner can normally be reached on Mon-Fri 8:30-5:50 PT.
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, Amandeep Saini can be reached on 571-272-3382. 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.
/QUN SHEN/
Primary Examiner, Art Unit 2662
Prosecution Insights