TY - GEN
T1 - Fidelity or Quality? A Region-Aware Framework for Enhanced Image Decoding via Hybrid Neural Networks
AU - Mao, Qi
AU - Wang, Shiqi
AU - Zhang, Xinfeng
AU - Wang, Shanshe
AU - Ma, Siwei
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/9
Y1 - 2019/9
N2 - The generative deep learning models such as the generative adversarial networks (GAN) have been shown to efficiently generate visually appealing images by learning the natural scene statistics. However, the signal fidelity, instead of the visual quality, has been largely ignored in the generation process, especially for the highly structural regions. In this paper, we introduce a region-aware visual signal restoration scheme to achieve a good balance between visual quality and fidelity. As a specific example of this framework, we develop an enhanced decoding scheme with hybrid neural networks, such that the base fidelity layer and texture quality enhancement layer are combined adaptively to restore the compressed images. The efficiency of the proposed framework is demonstrated with extensive experimental results, which show favorable performance against the state-of-the-art methods.
AB - The generative deep learning models such as the generative adversarial networks (GAN) have been shown to efficiently generate visually appealing images by learning the natural scene statistics. However, the signal fidelity, instead of the visual quality, has been largely ignored in the generation process, especially for the highly structural regions. In this paper, we introduce a region-aware visual signal restoration scheme to achieve a good balance between visual quality and fidelity. As a specific example of this framework, we develop an enhanced decoding scheme with hybrid neural networks, such that the base fidelity layer and texture quality enhancement layer are combined adaptively to restore the compressed images. The efficiency of the proposed framework is demonstrated with extensive experimental results, which show favorable performance against the state-of-the-art methods.
KW - enhanced image decoding
KW - fidelity
KW - generative adversarial networks
KW - Image restoration
KW - perceptual quality
UR - https://www.scopus.com/pages/publications/85076812411
U2 - 10.1109/ICIP.2019.8803229
DO - 10.1109/ICIP.2019.8803229
M3 - 会议稿件
AN - SCOPUS:85076812411
T3 - Proceedings - International Conference on Image Processing, ICIP
SP - 2616
EP - 2620
BT - 2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings
PB - IEEE Computer Society
T2 - 26th IEEE International Conference on Image Processing, ICIP 2019
Y2 - 22 September 2019 through 25 September 2019
ER -