ReflexSplit: Single Image Reflection Separation via Layer Fusion-Separation
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 hier archical 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.
Dual-branch encoders extract hierarchical features: GFEB (Swin Transformer) for global semantics {Pℓ} and LFEB (MuGI-based) for local textures {Eℓ}. CrGF adaptively aggregates these multi-scale features across decoder depths, while LFSB alternates between fusion (cross-stream complementarity) and differential separation (layer disentanglement) to progressively refine dual streams.
LFSB alternates between fusion (shared structure) and separation (layer disentanglement): (1) Bidirectional projection aligns transmission-reflection features; (2) Dual-dimensional attention (SA + CA) models spatial and inter-layer dependencies; (3) Differential operators A𝑡 − λℓA𝑟 suppress cross-stream interference; (4) FFNs with residuals integrate separated features.
DSRNet
MaxRF
DSIT
RDNet
Ours
On Real20, Nature, SIR2
On OpenRR
@article{lee2025reflexsplit,
title={ReflexSplit: Single Image Reflection Separation via Layer Fusion-Separation},
author={Chia-Ming Lee, Yu-Fan Lin, Jin-Hui Jiang, Yu-Jou Hsiao, Chih-Chung Hsu, Yu-Lun Liu},
journal={arXiv preprint arXiv:XXXX.XXXXX},
year={2025}
}