Abstract
We propose RetinexDualV2, a unified, physically grounded dual-branch framework for diverse Ultra-High-Definition (UHD) image restoration. Unlike generic models, our method employs a Task-Specific Physical Grounding Module (TS-PGM) to extract degradation-aware priors (e.g., rain masks and dark channels). These explicitly guide a Retinex decomposition network via a novel Physical-conditioned Multi-head Self-Attention (PC-MSA) mechanism, enabling robust reflection and illumination correction. This physical conditioning allows a single architecture to handle various complex degradations seamlessly, without task-specific structural modifications. RetinexDualV2 demonstrates exceptional generalizability, securing 4\textsuperscript{th} place in the NTIRE 2026 Day and Night Raindrop Removal Challenge and 5\textsuperscript{th} place in the Joint Noise Low-light Enhancement (JNLLIE) Challenge. Extensive experiments confirm the state-of-the-art performance and efficiency of our physically motivated approach.
Abstract (translated)
我们提出了RetinexDualV2，一个统一的、基于物理原理的双分支框架，用于处理多样化的超高清（UHD）图像恢复任务。与通用模型不同，我们的方法采用任务特定物理引导模块（TS-PGM）来提取退化感知先验（例如雨掩膜和暗通道）。这些先验通过一种新颖的物理条件多头自注意力（PC-MSA）机制，明确指导Retinex分解网络，从而实现鲁棒的反射和光照校正。这种物理条件化使得单一架构能够无缝处理各种复杂退化问题，而无需针对特定任务进行结构修改。RetinexDualV2展现出卓越的泛化能力，在NTIRE 2026昼夜雨滴去除挑战赛中位列第四，在联合噪声低光增强（JNLLIE）挑战赛中排名第五。大量实验验证了我们这种基于物理动机的方法具有卓越的性能和效率。
URL
https://arxiv.org/abs/2603.27979
