Unified ROI-based Image Compression Paradigm with Generalized Gaussian Model

TL;DR

This paper introduces a unified theoretical framework and a novel Generalized Gaussian Model for ROI-based image compression, significantly improving coding performance and downstream task accuracy by better modeling the distribution of semantic importance regions.

Contribution

It develops a rate-distortion optimization paradigm and proposes GGM with differentiable functions and a dynamic lower bound for stable training, outperforming Gaussian models in ROI coding.

Findings

Achieves state-of-the-art ROI reconstruction results.

Improves downstream task performance such as segmentation and detection.

Provides a more accurate distribution fit than classical models.

Abstract

Region-of-Interest (ROI)-based image compression allocates bits unevenly according to the semantic importance of different regions. Such differentiated coding typically induces a sharp-peaked and heavy-tailed distribution. This distribution characteristic mathematically necessitates a probability model with adaptable shape parameters for accurate description. However, existing methods commonly use a Gaussian model to fit this distribution, resulting in a loss of coding performance. To systematically analyze the impact of this distribution on ROI coding, we develop a unified rate-distortion optimization theoretical paradigm. Building on this paradigm, we propose a novel Generalized Gaussian Model (GGM) to achieve flexible modeling of the latent variables distribution. To support stable optimization of GGM, we introduce effective differentiable functions and further propose a dynamic lower bound to alleviate train-test mismatch. Moreover, finite differences are introduced to solve the gradient computation after GGM fits the distribution. Experiments on COCO2017 demonstrate that our method achieves state-of-the-art in both ROI reconstruction and downstream tasks (e.g., Segmentation, Object Detection). Furthermore, compared to classical probability models, our GGM provides a more precise fit to feature distributions and achieves superior coding performance. The project page is at https://github.com/hukai-tju/ROIGGM.