Single Image Reflection Separation via Component Synergy
This work addresses the challenge of reflection separation in images, which is important for applications like photography and computer vision, but it appears incremental as it builds on existing models.
The paper tackles the problem of separating reflections from a single image by proposing a more general superposition model with a learnable residue term and a novel network design, achieving superior performance over state-of-the-art methods on multiple real-world benchmark datasets.
The reflection superposition phenomenon is complex and widely distributed in the real world, which derives various simplified linear and nonlinear formulations of the problem. In this paper, based on the investigation of the weaknesses of existing models, we propose a more general form of the superposition model by introducing a learnable residue term, which can effectively capture residual information during decomposition, guiding the separated layers to be complete. In order to fully capitalize on its advantages, we further design the network structure elaborately, including a novel dual-stream interaction mechanism and a powerful decomposition network with a semantic pyramid encoder. Extensive experiments and ablation studies are conducted to verify our superiority over state-of-the-art approaches on multiple real-world benchmark datasets. Our code is publicly available at https://github.com/mingcv/DSRNet.