Context-Based Trit-Plane Coding for Progressive Image Compression

TL;DR

This paper introduces a novel context-based trit-plane coding algorithm for progressive image compression that improves rate-distortion performance by incorporating autoregressive context models and refining latent representations.

Contribution

The paper proposes the CTC algorithm with context-based modules for rate reduction and distortion refinement, enhancing progressive image compression beyond existing trit-plane methods.

Findings

Outperforms baseline trit-plane codec in BD-rate on Kodak dataset

Achieves better rate-distortion tradeoff with marginal increase in complexity

Demonstrates significant compression efficiency improvements

Abstract

Trit-plane coding enables deep progressive image compression, but it cannot use autoregressive context models. In this paper, we propose the context-based trit-plane coding (CTC) algorithm to achieve progressive compression more compactly. First, we develop the context-based rate reduction module to estimate trit probabilities of latent elements accurately and thus encode the trit-planes compactly. Second, we develop the context-based distortion reduction module to refine partial latent tensors from the trit-planes and improve the reconstructed image quality. Third, we propose a retraining scheme for the decoder to attain better rate-distortion tradeoffs. Extensive experiments show that CTC outperforms the baseline trit-plane codec significantly in BD-rate on the Kodak lossless dataset, while increasing the time complexity only marginally. Our codes are available at https://github.com/seungminjeon-github/CTC.