All-in-One Image Restoration via Causal-Deconfounding Wavelet-Disentangled Prompt Network

2026-03-04

AI Summary

Existing unified image restoration methods often suffer from limited generalization due to spurious correlations between semantic features and degradation patterns, as well as biases in degradation estimation. To address this, this work proposes CWP-Net, which introduces a causal disentanglement mechanism into the wavelet domain for the first time. Specifically, a wavelet attention module is employed to decouple semantic and degradation-related features, while a wavelet prompt block generates proxy variables to enable causal intervention. This approach effectively eliminates spurious associations and corrects degradation estimation bias. Extensive experiments under two All-in-One image restoration settings demonstrate that CWP-Net significantly outperforms current state-of-the-art methods, validating its effectiveness and superiority.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Machine Learning: Causal Learning
• Reasoning under Uncertainty: Causality

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Responsible Web: Measurement, analysis, and circumvention of Web censorship

Abstract

Image restoration represents a promising approach for addressing the inherent defects of image content distortion. Standard image restoration approaches suffer from high storage cost and the requirement towards the known degradation pattern, including type and degree, which can barely be satisfied in dynamic practical scenarios. In contrast, all-in-one image restoration (AiOIR) eliminates multiple degradations within a unified model to circumvent the aforementioned issues. However, according to our causal analysis, we disclose that two significant defects still exacerbate the effectiveness and generalization of AiOIR models: 1) the spurious correlation between non-degradation semantic features and degradation patterns; 2) the biased estimation of degradation patterns. To obtain the true causation between degraded images and restored images, we propose Causal-deconfounding Wavelet-disentangled Prompt Network (CWP-Net) to perform effective AiOIR. CWP-Net introduces two modules for decoupling, i.e., wavelet attention module of encoder and wavelet attention module of decoder. These modules explicitly disentangle the degradation and semantic features to tackle the issue of spurious correlation. To address the issue stemming from the biased estimation of degradation patterns, CWP-Net leverages a wavelet prompt block to generate the alternative variable for causal deconfounding. Extensive experiments on two all-in-one settings prove the effectiveness and superior performance of our proposed CWP-Net over the state-of-the-art AiOIR methods.

Problem

• all-in-one image restoration
• spurious correlation
• biased estimation
• degradation pattern
• image restoration

Innovation

• causal deconfounding
• wavelet disentanglement
• all-in-one image restoration
• spurious correlation
• prompt network