针对图像修复中多种退化干扰问题，提出自适应感知退化特征的动态调制方法。
Degradation-Aware Adaptive Context Gating for Unified Image Restoration
- 通过多尺度退化感知模块生成分层提示，动态调节注意力与特征融合
- 在单一模型下实现多种退化场景下的性能超越当前最优方法
- 适合需要统一处理复杂退化的实际图像修复任务
使用单一模型进行统一图像修复时常因多样退化导致任务干扰。为此，我们提出DACG-IR（退化感知自适应上下文门控），使模型能显式感知退化特征并动态调制特征表示。该方法从输入构建退化感知上下文表征，用于调节注意力分布、频域特征及特征聚合。具体地，轻量级多尺度退化感知模块提取粗粒度退化信息，并生成分层提示，指导编码器与解码器块中的注意力温度与输出门控，实现自适应特征提取。此外，空间-通道双门控自适应融合机制优化编码器特征，抑制噪声从浅层向深层传播。该设计有效抑制退化引入的噪声，同时保留关键结构信息。实验表明，DACG-IR在单任务、全功能、恶劣天气去除及复合退化场景下均优于现有最先进方法。代码：https://github.com/HlHomes/DACG-IR-code
原文摘要 · Abstract (English)
Unified image restoration using a single model often faces task interference due to diverse degradations. To address this, we propose DACG-IR (Degradation-Aware Adaptive Context Gating), which enables explicit perception of degradation characteristics to dynamically modulate feature representations. Our method constructs degradation-aware contextual representations from the input to modulate attention distribution, frequency-domain features, and feature aggregation. Specifically, a lightweight multi-scale degradation-aware module extracts coarse degradation information and generates layer-wise prompts. These prompts guide attention temperature and output gating in encoder and decoder blocks for adaptive feature extraction. Additionally, a spatial-channel dual-gated adaptive fusion mechanism refines encoder features, suppressing noise propagation from shallow to deep layers. This design effectively suppresses degradation-induced noise while preserving informative structures. Experiments show DACG-IR outperforms state-of-the-art methods in single-task, all-in-one, adverse weather removal, and composite degradation settings. Code: https://github.com/HlHomes/DACG-IR-code
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。