无遗忘恢复：跨图像退化的持续学习

中文摘要 AI 辅助

近期图像复原领域的进展已集中在采用一体化架构，该架构在单个网络内共同处理多种退化类型。这些方法在静态基准上表现有效，但针对的是封闭世界设定，假设在训练时可同时获取所有目标退化类型。实际应用中，现场部署的系统会逐步面临新的环境条件，因此会依次遇到不同的退化类型，且由于隐私或存储限制，通常无法获取历史训练数据。为适配新的退化类型，要么需要在所有先前数据的并集上重新训练，这往往成本高昂或不可行；要么需要微调，这会导致灾难性遗忘。我们将多退化图像复原问题表述为持续域增量学习问题，其中退化类型逐步到来且先前数据不可用。我们提出的无遗忘恢复（Restoring without Forgetting, RwF）框架为每种新退化类型学习一个轻量级适配器，通过架构设计消除遗忘，成本仅为专用域网络的一小部分。为隔离退化学习与数据集变化，我们构建了包含5种退化域的基准，这些退化域基于共享图像内容。测试时，无监督路由机制可在无需域标签的情况下为未知输入识别合适的复原路径。在5域序列任务中，RwF在Restormer和NAFNet骨干网络上的最终平均峰值信噪比（PSNR）较朴素顺序微调分别提升了15.25分贝和11.83分贝。该框架在11个标准真实退化基准（共3465张图像）上的路由准确率达89.5%，与神谕（oracle）PSNR的差距仅为+0.94分贝，据我们所知，这建立了首个针对持续多退化图像复原的系统基准。

英文摘要

Recent progress in image restoration has converged on all-in-one architectures that jointly handle multiple degradations within a single network. These methods are effective on static benchmarks but target a closed-world setting that assumes simultaneous access to every target degradation at training time. In practice, degradations are encountered sequentially as field-deployed systems progressively face new environmental conditions, and historical training data is often unavailable due to privacy or storage constraints. Accommodating a new degradation then requires either retraining on the union of all prior data, which is often costly or infeasible, or fine-tuning, which causes catastrophic forgetting. We formulate multi-degradation image restoration as a continual domain-incremental learning problem, in which degradations arrive incrementally and prior data is unavailable. Our proposed Restoring without Forgetting (RwF) framework learns a lightweight adapter for each new degradation, eliminating forgetting by construction at a fraction of the cost of dedicated per-domain networks. To isolate degradation learning from dataset variation, we construct a benchmark spanning five degradation domains under shared image content. At test time, an unsupervised routing mechanism identifies the appropriate restoration path for unknown inputs without requiring domain labels. Across the five-domain sequence, RwF improves final average PSNR over naive sequential fine-tuning by 15.25 dB and 11.83 dB on the Restormer and NAFNet backbones, respectively. The framework transfers to eleven canonical real-degradation benchmarks (3,465 images) at 89.5% routing accuracy with only a +0.94 dB oracle PSNR gap, establishing, to our knowledge, the first systematic baseline for continual multi-degradation image restoration.

发表机构

• Rochester Institute of Technology（罗切斯特理工学院）

机构由 AI 辅助整理，请以论文原文为准。