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 .
Priority
Receipt is acknowledged of certified copies of papers required by 37 CFR 1.55.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 5/5/2026 and 1/7/2025 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 § 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.
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) 1-7, 10 is/are rejected under 35 U.S.C. 103 as being unpatentable over Park et. al. (Korean Patent KR-20240131503-A) in view of Kong et. al. (Kong, Xiangtao et al. “ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data Characteristic.” 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021): 12011-12020.).
Regarding claim 1, Park et. al. discloses a device for generating super-resolution images through pixel level classification, the device comprising: an image input unit receiving a low-resolution image (Park et. al.: Figure 1, 2a: Reception of each low-resolution image within the input frame sequence (111, 113, 115); a backbone network unit providing the low-resolution image to a backbone network as input data to generate a low-resolution feature map as output data (Park et. al. [0039], Figure 2: The first layer of the trained backbone network (210) outputs features for a low-resolution image, and the first projection head receives the features and outputs a feature representation Zt from the features.); and a super-resolution image output unit generating a super-resolution image by outputting the upsampled specific pixel at the coordinates of the specific pixel of the low-resolution image (Park et. al.: Figure 1, [0061]: the super-resolution network (120) can generate a high-resolution image with less distortion and clarity by extracting feature representations at the pixel level, generating a clean image of a low-resolution image at the pixel level, and generating a high-resolution image by considering the pixel-level features of other images within the same frame sequence.).
However, Park et. al. fails to disclose a pixel classifier receiving the low-resolution feature map and coordinates of a specific pixel and determining an upsampler responsible for reconstruction by predicting reconstruction difficulty of the specific pixel; an upsampling unit including a plurality of upsamplers constructed based on the reconstruction difficulty and performing a pixel level operation which upsamples the specific pixel through the determined upsampler responsible for the reconstruction among the plurality of upsamplers.
Kong et. al. teaches a pixel classifier receiving the low-resolution feature map and coordinates of a specific pixel and determining an upsampler responsible for reconstruction by predicting reconstruction difficulty of the specific pixel (Kong et. al. Description: applies an super-resolution (SR)-module to perform SR for different classes, it first uses a class-module to classify the sub-images into different classes according to restoration. Based on this processing, we found that different image regions have different restoration efficiencies and can be processed by networks with different capacities.);
an upsampling unit including a plurality of upsamplers constructed based on the reconstruction difficulty and performing a pixel level operation which upsamples the specific pixel through the determined upsampler responsible for the reconstruction among the plurality of upsamplers (Kong et. al.: Description, abstract: intuitively, smooth areas are easier to super-solve than complex textures. To utilize this property, we can adopt appropriate SR networks to process different sub-images after the decomposition.).
These features are important to the claimed invention because the reconstruction process and upsampling unit enables learning and restoring missing high-frequency information in a lower resolution image. Upsampling allows for spatial expansion of the reconstructed features to match the target higher resolution image. Thus, it would have been obvious for one skilled in the art prior to the effective filing date of the claimed invention to have combined the teachings of Park et. al. and Kong et. al.
Regarding claim 10, which discloses a method for generating super-resolution images through pixel level classification performed by a device for generating super-resolution images through pixel level classification, which corresponds to the device of claim 1, which the rejection analysis is incorporated herein.
Regarding claim 2, Park et. al. and Kong et. al. disclose the device of claim1, and Park et. al. further discloses wherein the backbone network unit selects the Fast Super- Resolution Convolutional Neural Network (FSRCNN), the Cascading Residual Network (CARN), or the Super-Resolution Residual Network (SRResNet) as the backbone network based on reconstruction characteristics of the low-resolution image (Park et. al. [0035], Figure 2: the backbone network (210) is an image neural network, and as an example, the backbone network (210) can adopt the architecture of resnet18).
Regarding claim 3, Park et. al. and Kong et. al. disclose the device of claim 1, and Kong et. al. further discloses wherein the pixel classifier determines one of reconstruction difficulty levels assigned for processing to the plurality of upsamplers based on the low- resolution feature map as the reconstruction difficulty of the specific pixel (Kong et. al. abstract: easily derived from classifying sub-images into different classes according to a restoration difficulty level, then applying an SR-module so as to perform a super resolution (SR) suitable for each class, and differentially applying a capacity according to the difficulty level, or could be easily changed in the design).
Regarding claim 4, Park et. al. and Kong et. al. disclose the device of claim 1, and Kong et. al. further discloses wherein the pixel classifier determines an upsampler with a relatively large capacity if the specific pixel is composed of a relatively complex pattern or texture (Kong et. al. abstract: easily derived from classifying sub-images into different classes according to a restoration difficulty level, then applying an SR-module so as to perform a super resolution (SR) suitable for each class, and differentially applying a capacity according to the difficulty level, or could be easily changed in the design).
Regarding claim 5, Kong et. al. further discloses the device of claim 4, wherein the pixel classifier determines an upsampler with a relatively small capacity if the specific pixel is composed of a relatively simple pattern (Kong et. al. abstract: easily derived from classifying sub-images into different classes according to a restoration difficulty level, then applying an SR-module so as to perform a super resolution (SR) suitable for each class, and differentially applying a capacity according to the difficulty level, or could be easily changed in the design).
Regarding claim 6, Park et. al. and Kong et. al. disclose the device of claim 1, and Kong et. al. further discloses wherein the upsampling unit determines the reconstruction difficulty level based on the low-resolution feature map and determines the number of the plurality of upsamplers (Kong et. al. abstract: easily derived from classifying sub-images into different classes according to a restoration difficulty level, then applying an SR-module so as to perform a super resolution (SR) suitable for each class, and differentially applying a capacity according to the difficulty level, or could be easily changed in the design).
Regarding claim 7, Park et. al. and Kong et. al. disclose the device of claim l, and Kong et. al. further discloses wherein the upsampling unit implements the plurality of upsamplers to perform different upsampling techniques according to the reconstruction difficulty level (Kong et. al. abstract: easily derived from classifying sub-images into different classes according to a restoration difficulty level, then applying an SR-module so as to perform a super resolution (SR) suitable for each class, and differentially applying a capacity according to the difficulty level, or could be easily changed in the design).
Claim(s) 8-9 is/are rejected under 35 U.S.C. 103 as being unpatentable over Park et. al. (Korean Patent KR-20240131503-A) in view of Kong et. al. (Kong, Xiangtao et al. “ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data Characteristic.” 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021): 12011-12020.) as applied to claim 1 above, and further in view of Shi, Baoshun et al. “CTDNet: Cartoon-Texture Decomposition-based Gray Image Super-Resolution Network with Multiple Degradations.” Journal of the Optical Society of America B (2023): n. pag..
Regarding claim 8, Park et. al. and Kong et. al. disclose the device of claim 1. However, Park et. al. and Kong et. al. fail to disclose wherein the super-resolution image output unit performs pixel- wise refinement on the super-resolution image to post-process artifact pixels if discontinuity occurs between adjacent pixels reconstructed through the plurality of upsamplers.
Shi et. al. teaches wherein the super-resolution image output unit performs pixel- wise refinement on the super-resolution image to post-process artifact pixels if discontinuity occurs between adjacent pixels reconstructed through the plurality of upsamplers (Shi et. al. page 1: “for the SR task of refining real terahertz images, the boundary between the object of interest and the carrier table recovered by ctdnet has artifacts, which limits its realistic applications. To reduce these boundary artifacts, we post-process the SR terahertz images by using a boundary artifact reduction methods. It is determined that it can be easily derived by combining technical features or can be easily changed in design.).
This element is important to the claimed invention because image processing results in artifacts after reconstruction. Thus, it would have been obvious to one skilled in the art prior to the effective filing date of the claimed invention to have combined the teachings of Park et. al., Kong et. al. and Shi et. al. so that artifacts are removed.
Regarding claim 9, Park et. al. and Kong et. al. disclose the device of claim 1. However, Park et. al. and Kong et. al. fail to disclose wherein the super-resolution image output unit determines the discontinuity by applying Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), or Floating Point Operations (FLOPs) to the super-resolution image.
Shi et. al. teaches wherein the super-resolution image output unit determines the discontinuity by applying Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), or Floating Point Operations (FLOPs) to the super-resolution image (Shi et. al. page 1: “for the SR task of refining real terahertz images, the boundary between the object of interest and the carrier table recovered by ctdnet has artifacts, which limits its realistic applications. To reduce these boundary artifacts, we post-process the SR terahertz images by using a boundary artifact reduction methods. It is determined that it can be easily derived by combining technical features or can be easily changed in design.).
This element is important to the claimed invention because image processing results in artifacts and noise after reconstruction. Thus, it would have been obvious to one skilled in the art prior to the effective filing date of the claimed invention to have combined the teachings of Park et. al., Kong et. al. and Shi et. al. so that artifacts noise are removed.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JESSICA YIFANG LIN whose telephone number is (571)272-6435. The examiner can normally be reached M-F 7:00am-6:15pm, with optional day off.
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, Vu Le can be reached at 571-272-7332. 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.
/JESSICA YIFANG LIN/Examiner, Art Unit 2668 July 28, 2026
/VU LE/Supervisory Patent Examiner, Art Unit 2668
Prosecution Insights