A Cross Channel Context Model for Latents in Deep Image Compression
This work addresses image compression efficiency for applications like storage and transmission, offering incremental improvements over existing methods.
The paper tackles the problem of deep image compression by proposing a cross channel context model to capture correlations between different channels in latents, achieving BD-rate reductions of 6.30% and 6.31% over the baseline entropy model and 2.50% and 2.20% over VVC on standard datasets.
This paper presents a cross channel context model for latents in deep image compression. Generally, deep image compression is based on an autoencoder framework, which transforms the original image to latents at the encoder and recovers the reconstructed image from the quantized latents at the decoder. The transform is usually combined with an entropy model, which estimates the probability distribution of the quantized latents for arithmetic coding. Currently, joint autoregressive and hierarchical prior entropy models are widely adopted to capture both the global contexts from the hyper latents and the local contexts from the quantized latent elements. For the local contexts, the widely adopted 2D mask convolution can only capture the spatial context. However, we observe that there are strong correlations between different channels in the latents. To utilize the cross channel correlations, we propose to divide the latents into several groups according to channel index and code the groups one by one, where previously coded groups are utilized to provide cross channel context for the current group. The proposed cross channel context model is combined with the joint autoregressive and hierarchical prior entropy model. Experimental results show that, using PSNR as the distortion metric, the combined model achieves BD-rate reductions of 6.30% and 6.31% over the baseline entropy model, and 2.50% and 2.20% over the latest video coding standard Versatile Video Coding (VVC) for the Kodak and CVPR CLIC2020 professional dataset, respectively. In addition, when optimized for the MS-SSIM metric, our approach generates visually more pleasant reconstructed images.