提出 ReflexSplit 框架，解决单图像反射分离中的混合干扰问题。
ReflexSplit: Single Image Reflection Separation via Layer Fusion-Separation
- 采用跨尺度门控融合机制，增强多层特征一致性。
- 通过交替融合与分离块，实现传输与反射层精准解耦。
- 适合需要高保真反射分离的视觉应用，如图像修复与增强。
单图像反射分离（SIRS）旨在将混合图像分解为透射层和反射层。现有方法在非线性混合条件下易产生传输与反射混淆，尤其在深层解码器中，源于隐式融合机制和多尺度协调不足。本文提出 ReflexSplit，一种双流框架，包含三项创新：(1) 跨尺度门控融合（CrGF）自适应聚合分层深度下的语义先验、纹理细节与解码器上下文，稳定梯度流动并保持特征一致性；(2) 层融合-分离块（LFSB）交替执行共享结构提取的融合与层特定解耦的分离，受微分注意力启发，通过跨流减法实现双流分离；(3) 课程学习策略通过深度依赖初始化与逐轮预热逐步强化差异分离能力。在合成与真实世界基准上的大量实验表明，该方法达到当前最优性能，具备优异感知质量与鲁棒泛化能力。代码已开源：https://github.com/wuw2135/ReflexSplit。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。