IP Library › Granted Patent US 12,548,114
Granted Patent B2
US 12,548,114 · App. 17/972,034 · Granted Feb 10, 2026

Method for code-level super resolution and method for training super resolution model therefor

Inventors: Du Hyeon Bang (Seoul, KR); Seong Won Kim (Seoul, KR)
Assignee: SK Telecom Co., Ltd.
G06T3/4053G06T7/0002G06T9/00G06T2207/20081G06T2207/30168
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,548,114
App. No.
17/972,034
Granted
Feb 10, 2026
Kind
B2
Abstract

The present disclosure provides a method for code-level super-resolution imaging and a method of training a super-resolution model therefor. According to some embodiments, the present disclosure provides a method of training a super-resolution model based on the encoded codes of an inputted picture and a method for code-level super-resolution imaging by using a pre-trained super-resolution model.

Claims (26)

1 . A method of training to perform super-resolution imaging at a code level, the method comprising:

receiving an input picture;

generating a lowered-resolution picture from the received input picture;

generating input encoded codes by encoding the lowered-resolution picture;

providing the input encoded codes into a super-resolution model to generate, as prediction encoded codes, encoded codes of a high-resolution picture corresponding to the input encoded codes; and

training the super-resolution model based on a loss function defined as a combination of a first difference and a second difference, the first difference representing a difference between the input picture and a decoded version of the prediction encoded codes, and the second difference representing a difference between encoded codes of the input picture and the prediction encoded codes.

2 . The method of claim 1 , wherein the generation of the input encoded codes comprises down-sampling the input picture.

3 . The method of claim 1 , wherein the training of the super-resolution model comprises:

determining a perceptual loss by comparing a feature map extracted from a layer of the super-resolution model and a correct-answer set.

4 . A non-transitory computer-readable medium storing instructions thereon, the instructions when executed by one or more processors cause the one or more processor to: receive an input picture;

generate a lowered-resolution picture from the received input picture;

generate input encoded codes by encoding the lowered-resolution picture;

provide the input encoded codes into a super-resolution model to generate, as prediction encoded codes, encoded codes of a high-resolution picture corresponding to the input encoded codes; and

train the super-resolution model based on a loss function defined as a combination of a first difference and a second difference, the first difference representing a difference between the input picture and a decoded version of the prediction encoded codes, and the second difference representing a difference between encoded codes of the input picture and the prediction encoded codes.

5 . A method for super-resolution imaging by using a pre-trained super-resolution model to perform super-resolution imaging at a code level, the method comprising:

obtaining, as subject encoded codes, encoded codes of a subject picture;

providing the subject encoded codes into the pre-trained super-resolution model to generate prediction encoded codes, wherein the pre-trained super-resolution model is obtained by iteratively training based on a loss function defined as a combination of a first difference and a second difference, the first difference representing a difference between an input picture and a decoded version of encoded codes predicted by an untrained super-resolution model, and the second difference representing a difference between encoded codes of the input picture and the encoded codes predicted by the untrained super-resolution model;

decoding the prediction encoded codes to generate decoded prediction codes; and

generating a version of the subject picture with increased resolution based on the decoded prediction codes.

6 . The method of claim 5 , wherein the super-resolution model is trained further by:

receiving the input picture;

generating a lowered-resolution picture from the received input picture;

generating input encoded codes by encoding the lowered-resolution picture; and

providing the input encoded codes into the untrained super-resolution model to generate, as prediction encoded codes, encoded codes of a high-resolution picture corresponding to the input encoded codes.

7 . The method of claim 5 , wherein the subject encoded codes are generated by entropy decoding and de-quantizing a compressed picture.

8 . The method of claim 7 , wherein inverted discrete cosine transform (DCT) is performed on the prediction encoded codes to generate the version of the subject picture with increased resolution.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 24, 2022
From: BANG, DU HYEON; KIM, SEONG WON
To: SK TELECOM CO., LTD.
Reel/Frame 061520/0340 →
Priority Claims (1)
KR 10-2021-0142585 · Oct 25, 2021 · national
Continuity (1)
Related Publication 20230130288A1 · Apr 27, 2023
References Cited (14)
US 6256413B1 · Hirabayashi · 2001 [cited by examiner]
US 11849128B2 · Rippel · 2023 [cited by examiner]
US 20200034709A1 · Rippel · 2020 [cited by examiner]
US 20200082573A1 · Zhang · 2020 [cited by examiner]
US 20210084313A1 · Nguyen · 2021 [cited by examiner]
US 20210150660A1 · An · 2021 [cited by examiner]
US 20210287338A1 · Shih · 2021 [cited by examiner]
US 20220270207A1 · Chen · 2022 [cited by examiner]
US 20230130288A1 · Bang · 2023 [cited by examiner]
US 20230154132A1 · Oh · 2023 [cited by examiner]
US 20230267583A1 · Pranskevichus · 2023 [cited by examiner]
KR 101717377B1 · 2017 [cited by applicant]
T. Guo, H. Seyed Mousavi and V. Monga, “Adaptive Transform Domain Image Super-Resolution via Orthogonally Regularized Deep Networks,” in IEEE Transactions on Image Processing, vol. 28, No. 9, pp. 4685-4700, Sep. 2019, d… [cited by examiner]
Wenming Yang et al., “Deep Learning for Single Image Super-Resolution: A Brief Review”, arXiv:1808.03344v3 [cs.CV], Jul. 12, 2019, pp. 1-16. [cited by applicant]