DPICT: Deep Progressive Image Compression Using Trit-Planes

Jae-Han Lee, Seungmin Jeon, Kwang Pyo Choi, Youngo Park, Chang-Su Kim; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 16113-16122

Abstract

We propose the deep progressive image compression using trit-planes (DPICT) algorithm, which is the first learning-based codec supporting fine granular scalability (FGS). First, we transform an image into a latent tensor using an analysis network. Then, we represent the latent tensor in ternary digits (trits) and encode it into a compressed bitstream trit-plane by trit-plane in the decreasing order of significance. Moreover, within each trit-plane, we sort the trits according to their rate-distortion priorities and transmit more important information first. Since the compression network is less optimized for the cases of using fewer trit-planes, we develop a postprocessing network for refining reconstructed images at low rates. Experimental results show that DPICT outperforms conventional progressive codecs significantly, while enabling FGS transmission. Codes are available at https://github.com/jaehanlee-mcl/DPICT.

Related Material

[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lee_2022_CVPR, author = {Lee, Jae-Han and Jeon, Seungmin and Choi, Kwang Pyo and Park, Youngo and Kim, Chang-Su}, title = {DPICT: Deep Progressive Image Compression Using Trit-Planes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {16113-16122} }