English

One-to-Many Network for Visually Pleasing Compression Artifacts Reduction

Computer Vision and Pattern Recognition 2017-04-12 v2

Abstract

We consider the compression artifacts reduction problem, where a compressed image is transformed into an artifact-free image. Recent approaches for this problem typically train a one-to-one mapping using a per-pixel L2L_2 loss between the outputs and the ground-truths. We point out that these approaches used to produce overly smooth results, and PSNR doesn't reflect their real performance. In this paper, we propose a one-to-many network, which measures output quality using a perceptual loss, a naturalness loss, and a JPEG loss. We also avoid grid-like artifacts during deconvolution using a "shift-and-average" strategy. Extensive experimental results demonstrate the dramatic visual improvement of our approach over the state of the arts.

Keywords

Cite

@article{arxiv.1611.04994,
  title  = {One-to-Many Network for Visually Pleasing Compression Artifacts Reduction},
  author = {Jun Guo and Hongyang Chao},
  journal= {arXiv preprint arXiv:1611.04994},
  year   = {2017}
}
R2 v1 2026-06-22T16:53:25.334Z