Deep Back-Projection Networks for Super-Resolution

Muhammad Haris, Gregory Shakhnarovich, Norimichi Ukita; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 1664-1673

Abstract


The feed-forward architectures of recently proposed deep super-resolution networks learn representations of low-resolution inputs, and the non-linear mapping from those to high-resolution output. However, this approach does not fully address the mutual dependencies of low- and high-resolution images. We propose Deep Back-Projection Networks (DBPN), that exploit iterative up- and down-sampling layers, providing an error feedback mechanism for projection errors at each stage. We construct mutually-connected up- and down-sampling stages each of which represents different types of image degradation and high-resolution components. We show that extending this idea to allow concatenation of features across up- and down-sampling stages (Dense DBPN) allows us to reconstruct further improve super-resolution, yielding superior results and in particular establishing new state of the art results for large scaling factors such as 8x across multiple data sets.

Related Material


[pdf] [Supp] [arXiv]
[bibtex]
@InProceedings{Haris_2018_CVPR,
author = {Haris, Muhammad and Shakhnarovich, Gregory and Ukita, Norimichi},
title = {Deep Back-Projection Networks for Super-Resolution},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2018}
}