YASO

Dong Wei, Mei Yang; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2018, pp. 2625-2628

Abstract


This paper presents a lossy image compression methodbased on neural network. Our architecture just consists ofa recurrent neural network (RNN)-based encoder and decoder,a binarizer. This paper makes contributions in thefollowing two aspects: 1) Preprocess the input images sothat the encoder could work on images with arbitrary size;2) Optimize the number of output channels of the binarizer,and our method ensures that the compressed image usesless than 0.15 bpp; 3) Our network is suitable for highresolutionimages thanks to a sub-pixel architecture. As aconsequence, we find that the optimized method generallyexhibits better rate-distortion performance than standardJPEG compression methods on the Kodak dataset.

Related Material


[pdf]
[bibtex]
@InProceedings{Wei_2018_CVPR_Workshops,
author = {Wei, Dong and Yang, Mei},
title = {YASO},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2018}
}