Context-Based Trit-Plane Coding for Progressive Image Compression
This work addresses progressive image compression for applications requiring efficient storage and transmission, representing an incremental improvement over existing trit-plane methods.
The paper tackles the problem of progressive image compression by proposing context-based trit-plane coding (CTC), which outperforms the baseline trit-plane codec significantly in BD-rate on the Kodak lossless dataset with only a marginal increase in time complexity.
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.