通过进化调频实现图像修复的自适应动态调整
EvoIR: Towards All-in-One Image Restoration via Evolutionary Frequency Modulation
- 引入显式频域分解与自适应调制机制
- 在多个基准上超越现有最先进方法
- 适合需要处理多种退化场景的图像修复任务
全功能图像修复（AiOIR）常面临多样退化，需具备鲁棒且通用的策略。然而，现有方法普遍缺乏显式频域建模，依赖固定或启发式优化调度，限制了对异构退化的泛化能力。为此，我们提出EvoIR，一种面向AiOIR的框架，引入进化频域调制以实现动态自适应图像修复。具体地，EvoIR采用频域调制模块（FMM），显式将特征分解为高低频分支，并自适应调制以提升结构保真度与细粒度细节。核心在于进化优化策略（EOS），通过种群进化的迭代过程动态调整频域感知目标，平衡结构精度与感知保真度。其进化引导还能缓解跨退化梯度冲突，加速收敛。结合FMM与EOS，EvoIR性能优于单独使用任一组件，凸显其互补性。多基准实验证明，EvoIR显著优于当前最先进的AiOIR方法。
原文摘要 · Abstract (English)
All-in-One Image Restoration (AiOIR) tasks often involve diverse degradation that require robust and versatile strategies. However, most existing approaches typically lack explicit frequency modeling and rely on fixed or heuristic optimization schedules, which limit the generalization across heterogeneous degradation. To address these limitations, we propose EvoIR, an AiOIR-specific framework that introduces evolutionary frequency modulation for dynamic and adaptive image restoration. Specifically, EvoIR employs the Frequency-Modulated Module (FMM) that decomposes features into high- and low-frequency branches in an explicit manner and adaptively modulates them to enhance both structural fidelity and fine-grained details. Central to EvoIR, an Evolutionary Optimization Strategy (EOS) iteratively adjusts frequency-aware objectives through a population-based evolutionary process, dynamically balancing structural accuracy and perceptual fidelity. Its evolutionary guidance further mitigates gradient conflicts across degradation and accelerates convergence. By synergizing FMM and EOS, EvoIR yields greater improvements than using either component alone, underscoring their complementary roles. Extensive experiments on multiple benchmarks demonstrate that EvoIR outperforms state-of-the-art AiOIR methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。