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.

翻译：单图像反射分离（SIRS）旨在将混合图像解耦为透射层和反射层。现有方法在非线性混合条件下，特别是在深度解码器层中，由于隐式融合机制和多尺度协调不足，常出现透射-反射混淆问题。我们提出ReflexSplit，一种具有三个关键创新的双流框架。（1）跨尺度门控融合（CrGF）自适应地聚合跨层次深度的语义先验、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-分离块（LFSB）交替执行融合（用于提取共享结构）和差分分离（用于层特异性解耦）。受差分Transformer启发，我们通过跨流减法将注意力抵消机制扩展至双流分离。（3）课程训练通过深度依赖初始化和逐轮次预热逐步增强差分分离能力。在合成和真实世界基准上的大量实验表明，该方法取得了最先进的性能，具有优异的感知质量和鲁棒的泛化能力。我们的代码发布于 https://github.com/wuw2135/ReflexSplit。