Learning Accurate Entropy Model with Global Reference for Image Compression

Abstract

In recent deep image compression neural networks, the entropy model plays a critical role in estimating the prior distribution of deep image encodings. Existing methods combine hyperprior with local context in the entropy estimation function. This greatly limits their performance due to the absence of a global vision. In this work, we propose a novel Global Reference Model for image compression to effectively leverage both the local and the global context information, leading to an enhanced compression rate. The proposed method scans decoded latents and then finds the most relevant latent to assist the distribution estimating of the current latent. A by-product of this work is the innovation of a mean-shifting GDN module that further improves the performance. Experimental results demonstrate that the proposed model outperforms the rate-distortion performance of most of the state-of-the-art methods in the industry.

Cited by in corpus (5)

• MLIC: Multi-Reference Entropy Model for Learned Image Compression
• Contextformer: A Transformer with Spatio-Channel Attention for Context Modeling in Learned Image Compression
• LLIC: Large Receptive Field Transform Coding with Adaptive Weights for Learned Image Compression
• Spatiotemporal Entropy Model is All You Need for Learned Video Compression
• Learned Block-based Hybrid Image Compression