All-in-One Image Compression and Restoration

2025-02-05

AI Summary

Existing image compression methods suffer significant performance degradation on degraded images, while joint compression–restoration approaches are typically constrained to a single degradation type, limiting their applicability to real-world scenarios involving unknown, mixed degradations. To address this, we propose the first end-to-end learnable image codec framework explicitly designed for multi-degradation robustness. Our method decouples content information aggregation from degradation representation aggregation—enabling simultaneous compression and restoration without requiring explicit degradation priors. It integrates degradation-aware feature extraction, adaptive residual modeling, and joint rate-distortion optimization. Experiments demonstrate substantial improvements in rate-distortion performance across diverse synthetic and real-world degraded images, while maintaining full compatibility with clean images. The framework exhibits strong generalization capability and achieves over 30% faster inference speed compared to baseline methods.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Computer Vision: Learning & Optimization for CV
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Visual images corrupted by various types and levels of degradations are commonly encountered in practical image compression. However, most existing image compression methods are tailored for clean images, therefore struggling to achieve satisfying results on these images. Joint compression and restoration methods typically focus on a single type of degradation and fail to address a variety of degradations in practice. To this end, we propose a unified framework for all-in-one image compression and restoration, which incorporates the image restoration capability against various degradations into the process of image compression. The key challenges involve distinguishing authentic image content from degradations, and flexibly eliminating various degradations without prior knowledge. Specifically, the proposed framework approaches these challenges from two perspectives: i.e., content information aggregation, and degradation representation aggregation. Extensive experiments demonstrate the following merits of our model: 1) superior rate-distortion (RD) performance on various degraded inputs while preserving the performance on clean data; 2) strong generalization ability to real-world and unseen scenarios; 3) higher computing efficiency over compared methods. Our code is available at https://github.com/ZeldaM1/All-in-one.

Problem

• Unified image compression and restoration framework
• Handles various image degradations simultaneously
• Improves rate-distortion performance on degraded images

Innovation

• Unified image compression and restoration framework
• Content and degradation information aggregation
• Efficient handling of diverse image degradations