学习连续Wasserstein均值空间用于通用全合一图像修复
Learning Continuous Wasserstein Barycenter Space for Generalized All-in-One Image Restoration
AI总结：
本文提出BaryIR框架，通过Wasserstein均值空间对齐多源退化特征，解耦退化无关和退化特定信息，提升图像修复的泛化能力与鲁棒性。
摘要：
尽管在统一模型中针对多种退化问题实现了显著的全合一图像修复进展，但现有方法仍容易受到分布外退化的影响，从而限制了其在现实场景中的泛化能力。为解决这一挑战，本文受以下直觉的启发：多源退化特征分布是由不同退化特定的偏移从一个退化无关分布中诱导的，因此恢复这种共享分布对于在不同退化之间实现泛化至关重要。基于这一见解，我们提出BaryIR，一个表示学习框架，它在Wasserstein均值（WB）空间中对多源退化特征进行对齐，通过最小化到多源退化分布的Wasserstein距离的平均值来建模退化无关分布。我们进一步引入残差子空间，其嵌入在相互对比的同时保持与WB嵌入正交。因此，BaryIR显式地解耦了两个正交空间：一个编码跨退化共享的退化无关不变内容的WB空间，以及残差子空间，后者适应性地保留退化特定的知识。这种解耦减轻了对分布内退化的过拟合，并使基于退化无关共享不变性的自适应修复成为可能。广泛的实验表明，BaryIR在与最先进的全合一方法竞争时表现相当。值得注意的是，BaryIR能够很好地泛化到未见的退化（例如类型和级别），并且在训练时仅限于退化类型且在现实世界数据混合退化的情况下进行评估时，显示出显著的鲁棒性。
英文摘要：
Despite substantial advances in all-in-one image restoration for addressing diverse degradations within a unified model, existing methods remain vulnerable to out-of-distribution degradations, thereby limiting their generalization in real-world scenarios. To tackle the challenge, this work is motivated by the intuition that multisource degraded feature distributions are induced by different degradation-specific shifts from an underlying degradation-agnostic distribution, and recovering such a shared distribution is thus crucial for achieving generalization across degradations. With this insight, we propose BaryIR, a representation learning framework that aligns multisource degraded features in the Wasserstein barycenter (WB) space, which models a degradation-agnostic distribution by minimizing the average of Wasserstein distances to multisource degraded distributions. We further introduce residual subspaces, whose embeddings are mutually contrasted while remaining orthogonal to the WB embeddings. Consequently, BaryIR explicitly decouples two orthogonal spaces: a WB space that encodes the degradation-agnostic invariant contents shared across degradations, and residual subspaces that adaptively preserve the degradation-specific knowledge. This disentanglement mitigates overfitting to in-distribution degradations and enables adaptive restoration grounded on the degradation-agnostic shared invariance. Extensive experiments demonstrate that BaryIR performs competitively against state-of-the-art all-in-one methods. Notably, BaryIR generalizes well to unseen degradations (\textit{e.g.,} types and levels) and shows remarkable robustness in learning generalized features, even when trained on limited degradation types and evaluated on real-world data with mixed degradations.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
