ReflexSplit: Single Image Reflection Separation via Layer Fusion-Separation
Lee, Chia-Ming, Lin, Yu-Fan, Jiang, Jin-Hui, Hsiao, Yu-Jou, Hsu, Chih-Chung, Liu, Yu-Lun
原文摘要
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.
cs.CV
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表