Learned Image Compression with Enhanced Dynamic Spatial Aggregation and Asymmetric Entropy model

Learned image compression (LIC) has shown significant potential and better rate-distortion performance than traditional techniques. However, existing CNN-based approaches or window-based self-attention methods can only capture spatial information within fixed ranges. To tackle this limitation, we propose a novel method with dynamic spatial aggregation for transform coding. Our approach introduces enhanced adaptive aggregation, which generates kernel offsets to capture relevant information within content-dependent ranges, improving the transform process. Furthermore, we define a generalized coarse-to-fine entropy model that considers global context, channel-wise information, and spatial context in a coarse-to-fine manner. Additionally, our method takes into full consideration the model’s efficiency and complexity. By introducing the asymmetric entropy model structure and efficient heterogeneous convolution, our approach maintains lower coding complexity and higher decoding speed while ensuring performance. Experimental results demonstrate a substantial improvement in rate-distortion performance achieved by our method when compared to traditional compression methods like VTM and BPG, as well as some LIC methods.

I. Introduction

IN recent years, learned image compression (LIC) has revolutionized image compression. While traditional methods like JPEG [1] and VVC [2] have been the standard for visual data compression, the rapid progress in deep learning is leading us into a new era with data-driven approaches to overcome traditional limitations.