ReflexSplit：通过层融合-分离实现单图像反射分离
ReflexSplit: Single Image Reflection Separation via Layer Fusion-Separation
AI总结：
本文提出ReflexSplit框架，通过跨尺度门控融合、层融合-分离模块和课程学习方法，解决单图像反射分离中的传输-反射混淆问题，实现更高质量的分离效果。
摘要：
单图像反射分离（SIRS）将混合图像分解为传输层和反射层。现有方法在非线性混合下，特别是在深层解码器层中，由于隐式融合机制和多尺度协调不足而存在传输-反射混淆。我们提出ReflexSplit，一种双流框架，包含三个关键创新：（1）跨尺度门控融合（CrGF）适应性地聚合语义先验、纹理细节和解码器上下文，稳定梯度流并保持特征一致性。（2）层融合-分离模块（LFSB）在融合共享结构提取和差异分离层特定解构之间交替。受差分Transformer启发，我们通过跨流减法扩展注意力取消到双流分离。（3）课程训练通过深度依赖初始化和按epoch的预热逐步加强差异分离。在合成和现实基准上的广泛实验表明，该方法在感知质量和鲁棒泛化方面均优于现有方法。代码可在https://github.com/wuw2135/ReflexSplit获取。
英文摘要：
Single Image Reflection Separation (SIRS) disentangles mixed images into transmission and reflection layers. Existing methods suffer from transmission-reflection confusion under nonlinear mixing, particularly in deep decoder layers, due to implicit fusion mechanisms and inadequate multi-scale coordination. We propose ReflexSplit, a dual-stream framework with three key innovations. (1) Cross-scale Gated Fusion (CrGF) adaptively aggregates semantic priors, texture details, and decoder context across hierarchical depths, stabilizing gradient flow and maintaining feature consistency. (2) Layer Fusion-Separation Blocks (LFSB) alternate between fusion for shared structure extraction and differential separation for layer-specific disentanglement. Inspired by Differential Transformer, we extend attention cancellation to dual-stream separation via cross-stream subtraction. (3) Curriculum training progressively strengthens differential separation through depth-dependent initialization and epoch-wise warmup. Extensive experiments on synthetic and real-world benchmarks demonstrate state-of-the-art performance with superior perceptual quality and robust generalization. Our code is available at https://github.com/wuw2135/ReflexSplit.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
