ReflexSplit：基于层融合-分离的单图反射分离
ReflexSplit: Single Image Reflection Separation via Layer Fusion-Separation
把 Differential Transformer 的注意力相消机制推广到双流分离，用跨流相减显式抑制共享结构、放大层间差异，这一思路可直接迁移到去雨、去雾、去反光等需要解耦两个叠加成分的低层复原任务。
原文依据 Inspired by Differential Transformer, we extend attention cancellation to dual-stream separation via cross-stream subtraction.
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反射分离（SIRS）将混合图像解耦为透射层与反射层。现有方法在非线性混合条件下存在透射-反射混淆问题，尤其在深层解码器中，其原因在于隐式融合机制与多尺度协同不足。本文提出 ReflexSplit，一个包含三项关键创新的双流框架。（1）跨尺度门控融合（CrGF）在层级深度间自适应聚合语义先验、纹理细节与解码器上下文，稳定梯度流并保持特征一致性。（2）层融合-分离模块（LFSB）在用于共享结构提取的融合与用于层特定解耦的差分分离之间交替进行。受 Differential Transformer 启发，我们通过跨流相减将注意力相消扩展到双流分离。（3）课程训练通过深度相关初始化与按轮次预热逐步增强差分分离。在合成与真实基准上的大量实验表明，该方法取得了最优性能，具有更优的感知质量与稳健的泛化能力。
英文原文摘要 1172 字符
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.