From Physical Degradation Models to Task-Aware All-in-One Image Restoration

2026-01-15

AI Summary

This work addresses the limitations of existing general-purpose image restoration methods, which often suffer from structural complexity due to additional learning modules, hindering real-time deployment, and neglect the explicit modeling of physical degradation processes. To overcome these issues, the authors propose OPIR, a two-stage physically grounded restoration framework. In the first stage, OPIR predicts a task-aware inverse degradation operator to generate an initial restoration result along with an uncertainty map; in the second stage, this uncertainty guides a refinement process for enhanced output quality. By integrating task-aware parameter injection, inverse degradation operator prediction, and convolution acceleration mechanisms, OPIR achieves a compact architecture that balances computational efficiency and restoration performance, attaining state-of-the-art results on both general and task-specific image restoration benchmarks.

Technology Category

• Computer Vision: Low Level & Physics-based Vision
• Search and Optimization: Learning to Search
• Planning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

• 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
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

All-in-one image restoration aims to adaptively handle multiple restoration tasks with a single trained model. Although existing methods achieve promising results by introducing prompt information or leveraging large models, the added learning modules increase system complexity and hinder real-time applicability. In this paper, we adopt a physical degradation modeling perspective and predict a task-aware inverse degradation operator for efficient all-in-one image restoration. The framework consists of two stages. In the first stage, the predicted inverse operator produces an initial restored image together with an uncertainty perception map that highlights regions difficult to reconstruct, ensuring restoration reliability. In the second stage, the restoration is further refined under the guidance of this uncertainty map. The same inverse operator prediction network is used in both stages, with task-aware parameters introduced after operator prediction to adapt to different degradation tasks. Moreover, by accelerating the convolution of the inverse operator, the proposed method achieves efficient all-in-one image restoration. The resulting tightly integrated architecture, termed OPIR, is extensively validated through experiments, demonstrating superior all-in-one restoration performance while remaining highly competitive on task-aligned restoration.

Problem

• all-in-one image restoration
• task-aware restoration
• physical degradation modeling
• real-time applicability
• system complexity

Innovation

• task-aware restoration
• inverse degradation operator
• uncertainty perception
• physical degradation modeling
• all-in-one image restoration