Efficient Screen Content Image Compression via Superpixel-based Content Aggregation and Dynamic Feature Fusion

Efficient Screen Content Image Compression via Superpixel-based Content Aggregation and Dynamic Feature Fusion

Sheng Shen, Huanjing Yue, Jingyu Yang

Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence
Main Track. Pages 1209-1217. https://doi.org/10.24963/ijcai.2024/134

This paper addresses the challenge of efficiently compressing screen content images (SCIs) – computer generated images with unique attributes such as large uniform regions, sharp edges, and limited color palettes, which pose difficulties for conventional compression algorithms. We propose a Superpixel-based Content Aggregation Block (SCAB) to aggregate local pixels into one super-pixel and aggregate non-local information via super-pixel transformer. Such aggregation enables the dynamic assimilation of non-local information while maintaining manageable complexity. Furthermore, we enhance our channel-wise context entropy model with a Dynamic Feature Fusion (DFF) mechanism. This mechanism integrates decoded slices and side information dynamically based on their global correlation, allowing the network to dynamically learn the optimal weights for global information usage. Extensive experiments on three SCI datasets (SCID, CCT, and SIQAD) show our method’s superior RD performance and inference time, making it the first network comparable with the advanced VVC-SCC standard.
Keywords:
Computer Vision: CV: Image and video synthesis and generation 
Computer Vision: CV: Computational photography
Computer Vision: CV: Other