EvReflection: Event-Driven Micro-Dynamics for Reflection Removal

Reflection removal is a highly challenging problem. Though remarkable progress has been made, current methods primarily exploit static image priors from a single frame. Due to the inherent ambiguity between layers, existing methods still suffer from severe residual artifacts. In this paper, we propose leveraging event signals to break this ambiguity. By employing event cameras to capture micro-dynamics, we reveal the differential motion between the reflection and background layers. We thereby present a novel event-driven reflection removal network, EvReflection, that utilizes these dynamic cues for layer separation. Specifically, we design a Micro-Dynamics Decoupler to disentangle layer-specific motions from event streams as priors, which then guide a Parallax-Attention Rectifier to cleanly remove artifacts from the RGB image. Furthermore, to address the data shortage, we develop a physics-based simulation pipeline and construct the EVR$^2$ benchmark, the first real-world dataset for this task. Extensive experiments demonstrate that EvReflection significantly outperforms existing methods, recovering clean images in challenging real-world scenarios.