Abstract

A very deep convolutional neural network (CNN) has recently achieved great success for image super-resolution (SR) and offered hierarchical features as well. However, most deep CNN based SR models do not make full use of the hierarchical features from the original low-resolution (LR) images, thereby achieving relatively-low performance. In this paper, we propose a novel residual dense network (RDN) to address this problem in image SR. We fully exploit the hierarchical features from all the convolutional layers. Specifically, we propose residual dense block (RDB) to extract abundant local features via dense 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 (CM) mechanism. Local feature fusion in RDB is then used to adaptively learn more effective features from preceding and current local features and stabilizes the training of wider network. After fully obtaining dense local features, we use global feature fusion to jointly and adaptively learn global hierarchical features in a holistic way. Experiments on benchmark datasets with different degradation models show that our RDN achieves favorable performance against state-of-the-art methods.

Keywords

Convolutional neural networkResidualBenchmark (surveying)Computer scienceFeature (linguistics)Pattern recognition (psychology)Block (permutation group theory)Artificial intelligenceImage (mathematics)SuperresolutionImage resolutionExploitAlgorithmMathematics

Affiliated Institutions

Related Publications

Publication Info

Year
2018
Type
article
Pages
2472-2481
Citations
3866
Access
Closed

External Links

Social Impact

Social media, news, blog, policy document mentions

Citation Metrics

3866
OpenAlex

Cite This

Yulun Zhang, Yapeng Tian, Yu Kong et al. (2018). Residual Dense Network for Image Super-Resolution. , 2472-2481. https://doi.org/10.1109/cvpr.2018.00262

Identifiers

DOI
10.1109/cvpr.2018.00262