Residual Dense Network for Image Restoration

• Published in: IEEE transactions on pattern analysis and machine intelligence Vol. 43; no. 7; pp. 2480 - 2495
• Main Authors: Zhang, Yulun, Tian, Yapeng, Kong, Yu, Zhong, Bineng, Fu, Yun
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.07.2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial neural networks; compression artifact reduction; Feature extraction; hierarchical features; Image coding; Image compression; image deblurring; Image denoising; Image quality; Image resolution; Image restoration; image super-resolution; Noise reduction; Residual dense network; Task analysis; Training
• ISSN: 0162-8828; 1939-3539; 2160-9292
• DOI: 10.1109/TPAMI.2020.2968521

Recently, deep convolutional neural network (CNN) has achieved great success for image restoration (IR) and provided hierarchical features at the same time. However, most deep CNN based IR models do not make full use of the hierarchical features from the original low-quality images; thereby, resulting in relatively-low performance. In this work, we propose a novel and efficient residual dense network (RDN) to address this problem in IR, by making a better tradeoff between efficiency and effectiveness in exploiting the hierarchical features from all the convolutional layers. Specifically, we propose residual dense block (RDB) to extract abundant local features via densely connected convolutional layers. RDB further allows direct connections from the state of preceding RDB to all the layers of current RDB, leading to a contiguous memory mechanism. To adaptively learn more effective features from preceding and current local features and stabilize the training of wider network, we proposed local feature fusion in RDB. After fully obtaining dense local features, we use global feature fusion to jointly and adaptively learn global hierarchical features in a holistic way. We demonstrate the effectiveness of RDN with several representative IR applications, single image super-resolution, Gaussian image denoising, image compression artifact reduction, and image deblurring. Experiments on benchmark and real-world datasets show that our RDN achieves favorable performance against state-of-the-art methods for each IR task quantitatively and visually.