Trash or Treasure? An Interactive Dual-Stream Strategy for Single Image Reflection Separation

Single image reflection separation (SIRS), as a representative blind source separation task, aims to recover two layers, i.e., transmission and reflection, from one mixed observation, which is challenging due to the highly ill-posed nature. Existing deep learning based solutions typically restore the target layers individually, or with some concerns at the end of the output, barely taking into account the interaction across the two streams/branches. In order to utilize information more efficiently, this work presents a general yet simple interactive strategy, namely your trash is my treasure (YTMT), for constructing dual-stream decomposition networks. To be specific, we explicitly enforce the two streams to communicate with each other block-wisely. Inspired by the additive property between the two components, the interactive path can be easily built via transferring, instead of discarding, deactivated information by the ReLU rectifier from one stream to the other. Both ablation studies and experimental results on widely-used SIRS datasets are conducted to demonstrate the efficacy of YTMT, and reveal its superiority over other state-of-the-art alternatives. The implementation is quite simple and our code is publicly available at https://github.com/mingcv/YTMT-Strategy . * Corresponding Author 1 Many problems follow the same additive model, such as denoising (I = B + N , where B and N denote clean image and noise, respectively), and intrinsic image decomposition (log I = log A + log S, where A and S stand for albedo and shading, respectively.) The proposed strategy can be potentially applied to all these tasks, but due to page limit, we concentrate on the task of SIRS to verify primary claims in this paper. 35th Conference on Neural Information Processing Systems (NeurIPS 2021).