LightRR：一种用于单图像去反射的轻量级网络
LightRR: A Lightweight Network for Single Image Reflection Removal
把 DWT 频域分解与 Mamba 状态空间建模结合成非对称频域模块，在低分辨率子带上做长程依赖建模，为轻量化复原网络提供了可复用的频域-序列混合骨干设计；同时用知识蒸馏把大预训练编码器的表征迁移到小模型，是低算力部署场景下值得借鉴的训练范式。
原文依据 an Asymmetric Frequency Mamba Block (AFM), which leverages the Discrete Wavelet Transform (DWT) to decompose features into low- and high-frequency components
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论单图像去反射（SIRR）是一个高度病态且计算代价高昂的问题。现有的基于 CNN 或 Transformer 的方法往往依赖大感受野与繁重计算，限制了其在资源受限设备上的部署。为此，我们提出 LightRR，一个轻量却有效的去反射网络，它将基于小波的机制与状态空间建模（SSM）统一起来。具体而言，我们引入非对称频域 Mamba 模块（AFM），利用离散小波变换（DWT）将特征分解为低频与高频分量，从而通过基于 Mamba 的状态空间动力学对特定频率的依赖关系进行有针对性的建模。该设计不仅能高效捕获长程上下文，还在保留关键细节的同时降低了空间分辨率与计算量。此外，经知识蒸馏增强的编码器使网络在训练期间能够继承大型预训练模型的表征能力，从而实现轻量级推理。在多个真实世界基准上的大量实验表明，LightRR 取得了与最优方法相当的性能，而参数量仅为 RDNet 的 3.01%、浮点运算量仅为 5.22%，凸显了其在精度与效率之间的优越平衡。
英文原文摘要 1335 字符
Single-image reflection removal (SIRR) is a highly ill-posed and computationally demanding problem. Existing CNN or Transformer-based methods often rely on large receptive fields and heavy computation, limiting their deployment on resource-constrained devices. To address this, we propose LightRR, a lightweight yet effective reflection removal network that unifies a wavelet-based mechanism and State Space Modeling (SSM).Specifically, we introduce an Asymmetric Frequency Mamba Block (AFM), which leverages the Discrete Wavelet Transform (DWT) to decompose features into low- and high-frequency components. This allows for targeted modeling of frequency-specific dependencies via Mamba-based state space dynamics.This design not only captures long-range context efficiently but also reduces spatial resolution and computation while preserving critical details.Furthermore, a knowledge distillation-enhanced encoder allows the network to inherit the representational power of large pre-trained models during training, enabling lightweight inference.Extensive experiments on multiple real-world benchmarks demonstrate that LightRR achieves performance comparable to state-of-the-art methods, while using only 3.01% of the parameters and 5.22% of the FLOPs (vs. RDNet), highlighting its superior balance between accuracy and efficiency.