상세정보
학술대회
A Training Method for Image Compression Networks to Improve Perceptual Quality of Reconstructions
- 발행일
- 202006
- 출처
- Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) 2020, pp.585-589
- 협약과제
- 20HH2300, [통합과제] 초실감 테라미디어를 위한 AV부호화 및 LF미디어 원천기술 개발, 최진수
- 초록
- Recently, neural-network based lossy image compression methods have been actively studied and they have achieved remarkable performance. However, the classical evaluation metrics, such as PSNR and MS-SSIM, that the recent approaches have been using in their objective function yield sub-optimal coding efficiency in terms of human perception, although they are very dominant metrics in research and standardization fields. Taking into account that improving the perceptual quality is one of major goals in lossy image compression, we propose a new training method that allows the existing image compression networks to reconstruct perceptually enhanced images. By experiments, we show the effectiveness of our method, both quantitatively and qualitatively.
- KSP 제안 키워드
- Coding efficiency, Compression method, Perceptual Quality, evaluation metrics, human perception, lossy image compression, neural network, objective function, training method