CNN-Optimized Image Compression with Uncertainty based Resource Allocation

Zhenzhong Chen, Yiming Li, Feiyang Liu, Zizheng Liu, Xiang Pan, Wanjie Sun, Yingbin Wang, Yan Zhou, Han Zhu, Shan Liu; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2018, pp. 2559-2562

Abstract

In this paper, we provide the description of our approach designed for participating the CVPR 2018 Challenge on Learned Image Compression (CLIC). Our approach is a hybrid image coder based on CNN-optimized in-loop filter and mode coding, with uncertainty based resource allocation for compressing the task images. Two solutions were submitted, i.e., "iipTiramisu" and its speedup version "iip-TiramisuS", resulting in 32.14 dB and 32.06 dB in PSNR, respectively. These two results have been ranked No. 1 and 2 on the leaderboard.

Related Material

[pdf]
[bibtex]
@InProceedings{Chen_2018_CVPR_Workshops,
author = {Chen, Zhenzhong and Li, Yiming and Liu, Feiyang and Liu, Zizheng and Pan, Xiang and Sun, Wanjie and Wang, Yingbin and Zhou, Yan and Zhu, Han and Liu, Shan},
title = {CNN-Optimized Image Compression with Uncertainty based Resource Allocation},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2018}
}