ResGAN: A Low-Level Image Processing Network to Restore Original Quality of JPEG Compressed Images

• Published in: 2019 Data Compression Conference (DCC) p. 616
• Main Authors: Zhu, Chunbiao, Chen, Yuanqi, Zhang, Yiwei, Liu, Shan, Li, Ge
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.03.2019
• Subjects: Compressed Image Restoration; Image coding; Image denoising; Image restoration; Loss measurement; Low Level Image Processing Network; Optimization; ResGAN; Task analysis
• ISSN: 2375-0359
• DOI: 10.1109/DCC.2019.00128

Low-level image processing is mainly concerned with extracting descriptions (that are usually represented as images themselves) from images. With the rapid development of neural networks, many deep learning-based low-level image processing tasks have shown outstanding performance. In this paper, we describe a unified deep learning based approach for low-level image processing, in particular, image denoising, image deblurring, and compressed image restoration. The proposed method is composed of deep convolutional neural and conditional generative adversarial networks. For the discriminator network, we present a new network architecture with bi-skip connections to address hard training and details losing issues. In the generative network, a multi-objective optimization is derived to solve the problem of common conditions being non-identical. Through extensive experiments on three low-level image processing tasks on both qualitative and quantitative criteria, we demonstrate that our proposed method performs favorably against all current state-of-the-art approaches.