Language-guided Image Reflection Separation
This addresses a domain-specific problem in computer vision for applications like image enhancement, but it is incremental as it builds on prior reflection separation work by adding language guidance.
The paper tackles the ill-posed problem of reflection separation in images by introducing language descriptions to guide the process, achieving significant performance advantages over existing methods in quantitative and qualitative comparisons.
This paper studies the problem of language-guided reflection separation, which aims at addressing the ill-posed reflection separation problem by introducing language descriptions to provide layer content. We propose a unified framework to solve this problem, which leverages the cross-attention mechanism with contrastive learning strategies to construct the correspondence between language descriptions and image layers. A gated network design and a randomized training strategy are employed to tackle the recognizable layer ambiguity. The effectiveness of the proposed method is validated by the significant performance advantage over existing reflection separation methods on both quantitative and qualitative comparisons.