ECCV 2014 - LNCS 8689-8695

Deep Network Cascade for Image Super-resolution

Zhen Cui^{1, 2}, Hong Chang¹, Shiguang Shan¹, Bineng Zhong², and Xilin Chen¹

¹Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS, Beijing, China
zhen.cui@vipl.ict.ac.cn
hong.chang@vipl.ict.ac.cn
sgshan@ict.ac.cn
xlchen@ict.ac.cn

²School of Computer Science and Technology, Huaqiao University, Xiamen, China
bnzhong@hqu.edu.cn

Abstract. In this paper, we propose a new model called deep network cascade (DNC) to gradually upscale low-resolution images layer by layer, each layer with a small scale factor. DNC is a cascade of multiple stacked collaborative local auto-encoders. In each layer of the cascade, non-local self-similarity search is first performed to enhance high-frequency texture details of the partitioned patches in the input image. The enhanced image patches are then input into a collaborative local auto-encoder (CLA) to suppress the noises as well as collaborate the compatibility of the overlapping patches. By closing the loop on non-local self-similarity search and CLA in a cascade layer, we can refine the super-resolution result, which is further fed into next layer until the required image scale. Experiments on image super-resolution demonstrate that the proposed DNC can gradually upscale a low-resolution image with the increase of network layers and achieve more promising results in visual quality as well as quantitative performance.

Keywords: Super-resolution, Auto-encoder, Deep learning

LNCS 8693, p. 49 ff.

Full article in PDF | BibTeX