For learned image compression, the autoregressive context model is proved effective in improving the rate-distortion (RD) performance. Because it helps remove spatial redundancies among latent representations. However, the decoding process must be done in a strict scan order, which breaks the parallelization. We propose a parallelizable checkerboard context model (CCM) to solve the problem. Our two-pass checkerboard context calculation eliminates such limitations on spatial locations by re-organizing the decoding order. Speeding up the decoding process more than 40 times in our experiments, it achieves significantly improved computational efficiency with almost the same rate-distortion performance. To the best of our knowledge, this is the first exploration on parallelization-friendly spatial context model for learned image compression.
@article{arxiv.2103.15306,
title = {Checkerboard Context Model for Efficient Learned Image Compression},
author = {Dailan He and Yaoyan Zheng and Baocheng Sun and Yan Wang and Hongwei Qin},
journal= {arXiv preprint arXiv:2103.15306},
year = {2021}
}