지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
논문 기본 정보
- 자료유형
- 학술저널
- 저자정보
- 저널정보
- 대한전자공학회 IEIE Transactions on Smart Processing & Computing IEIE Transactions on Smart Processing & Computing Vol.9 No.1
- 발행연도
- 2020.2
- 수록면
- 1 - 6 (6page)
- DOI
- 10.5573/IEIESPC.2020.9.1.001
이용수
초록· 키워드
오류제보하기
High Efficiency Video Coding (HEVC) is a widely used video compression standard that minimizes the sacrifice in visual quality. Convolutional neural networks (CNNs) are being used as a post-processing tool for video restoration degraded by compression. Improving on CNN-based video restoration, this paper attempts a new generative adversarial network (GAN)-based video restoration called a compressed video restoration generative adversarial network (CVRGAN). Although a GAN is widely used for perceptual image enhancement in super-resolution and noise reduction, it is not yet used for compressed video restoration. The proposed CVRGAN is the first attempt to utilize a GAN to create the texture of a degraded image, and consequently, to generate detailed textures that were lost due to compression. In order to avoid the side effect of a GAN boosting the blocking and ringing artifacts incurred by compression, the CVRGAN employs a new content loss that is a combination of VGG feature difference, which represents a perceptual loss, and an objective loss, such as mean squared error (MSE) or mean absolute error (MAE). The new loss function is effective in the enhancement of subjective image quality while suppressing artifact boosting. An extensive mean opinion score (MOS) test shows that the CVRGAN achieves an improvement in perceptual quality over previous CNN-based video restoration.
목차
Abstract
1. Introduction
2. Image Enhancement with a Generative Adversarial Network
3. The Proposed Compressed Video Restoration
4. Experiments
5. Conclusion
References
참고문헌 (16)
참고문헌 신청
A. Norkin / 2012 / HEVC deblocking filter / IEEE Trans. Circuits Syst. Video Technol 22(12):1746~1754
C. Chen / 2015 / Adaptive guided image filter for improved in-loop filtering in video coding / IEEE Workshop on Multimedia. Signal Processing
J. Hou / 2017 / Quality enhancement of compressed video via CNNs / Journal of Information Hiding and Multimedia Signal Processing 8(1)
J. Kim / 2016 / Accurate image super-resolution using very deep convolutional networks / Proc. of IEEE Conf. Comput. Vis. Pattern Recognit :1646~1654
Dong / 2015 / Compression artifacts reduction by a deep convolutional network / Proc. of IEEE Conf. Comput. Vis. Pattern Recognit :576~584
C. Chen / 2015 / Adaptive guided image filter for improved in-loop filtering in video coding / IEEE Workshop on Multimedia. Signal Processing
J. Hou / 2017 / Quality enhancement of compressed video via CNNs / Journal of Information Hiding and Multimedia Signal Processing 8(1)
J. Kim / 2016 / Accurate image super-resolution using very deep convolutional networks / Proc. of IEEE Conf. Comput. Vis. Pattern Recognit :1646~1654
Dong / 2015 / Compression artifacts reduction by a deep convolutional network / Proc. of IEEE Conf. Comput. Vis. Pattern Recognit :576~584
함께 읽어보면 좋을 논문
논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!
-
Constrained adversarial loss for generative adversarial network?based faithful image restoration
[ETRI] ETRI Journal
2019 .08
-
GAN 을 이용한 압축된 동영상 품질 향상
한국방송미디어공학회 학술발표대회 논문집
2022 .11
-
A Comparative study on Generative Adversarial Network (GAN)
대한전자공학회 학술대회
2020 .11
-
GAN을 활용한 데이터 생성 연구 동향
한국항공우주학회 학술발표회 초록집
2023 .06
-
New Link Prediction Algorithm using Generative Adversarial Network(GAN)
대한산업공학회 춘계공동학술대회 논문집
2018 .04
-
GAN을 이용한 데이터 불균형 문제에 관한 연구
한국통신학회 학술대회논문집
2019 .01
-
2D 이미지를 이용한 3D 얼굴 생성 과정에서 GAN을 이용한 얼굴 texture 복원에 관한 연구
대한전자공학회 학술대회
2024 .06
-
Versatile Video Coding을 활용한 Video based Point Cloud Compression 방법
한국방송미디어공학회 학술발표대회 논문집
2020 .07
-
압축 왜곡 감소를 위한 CNN 기반 이미지 화질개선 알고리즘
멀티미디어학회논문지
2022 .05
-
GAN 을 활용한 경로 손실 예측 기법
한국통신학회 학술대회논문집
2023 .06
-
A Video Coding System based on Coefficient Modeling Considering Visual Artifact
대한전자공학회 학술대회
2017 .01
-
Generation of Artificial Images/Videos of Natural Disaster Using GAN
제어로봇시스템학회 국내학술대회 논문집
2020 .07
-
딥러닝을 활용한 동영상 압축·복원 기술에 관한 연구
한국정보과학회 학술발표논문집
2017 .12
-
Morpho-GAN: Unsupervised Learning of Data with High Morphology using Generative Adversarial Networks
한국컴퓨터정보학회 학술발표논문집
2020 .01
-
적대적 생성 신경망기반 데이터 증강을 통한 해상객체 식별 성능향상에 대한 연구
대한전자공학회 학술대회
2021 .06
-
HEVC 비디오 영상 압축 왜곡 제거를 위한 Generative Adversarial Network 적용 기법
한국방송미디어공학회 학술발표대회 논문집
2017 .06
-
잡음제거 합성곱 신경망을 이용한 이미지 복원 방법
멀티미디어학회논문지
2022 .01
-
Efficient Image Size Selection for MPEG Video-based Point Cloud Compression
한국방송미디어공학회 학술발표대회 논문집
2022 .06
-
GAN 알고리즘을 이용한 음악 생성
한국컴퓨터정보학회 학술발표논문집
2018 .07
-
Improving Super-Resolution GAN Performance through Discriminator using U-Net Structure and Auxiliary Classifier
Journal of KIISE
2021 .11
이 논문의 저자 정보
이 논문과 함께 이용한 논문
Bit-width Reduction in Write Counters for Wear Leveling in a Phase-change Memory System
Hyokeun Lee
,
Hyunmin Jung
,
Hyuk-Jae Lee
외 1명
IEIE Transactions on Smart Processing & Computing
2020
.10
Extraction of Key Frames from Dance Videos and Movement Recognition by Multi-feature Fusion
Jie Yan
IEIE Transactions on Smart Processing & Computing
2023
.12
Dynamic Framerate SlowFast Network for Improving Autonomous Driving Performance
Byeong-Uk Jeon
,
Kyungyong Chung
IEIE Transactions on Smart Processing & Computing
2023
.06
Overview of Versatile Video Coding (H.266/VVC) and Its Coding Performance Analysis
Minhun Lee
,
HyeonJu Song
,
Jeeyoon Pa
외 7명
IEIE Transactions on Smart Processing & Computing
2023
.04
비디오 코딩을 위한 분산에 따른 적응적 Guided Image Filter
이주한
,
김태성
,
이유학
외 1명
대한전자공학회 학술대회
2018
.06
최근 본 자료
댓글(0)
0