Fast User-Guided Single Image Reflection Removal via Edge-Aware Cascaded Networks

Taking photos through a glass window leads to glare or reflection, which might distract the viewer from the scene behind the window. In this paper, we involve user interaction to tackle the ill-posedness of the reflection removal problem. Users are allowed to draw strokes or lassos to indicate the background and reflection layers. Instead of designing hand-crafted features, we propose the edge-aware cascaded networks for reflection removal. The proposed network is a two-stage pipeline. The first stage takes the edge hints converted from user guidance and the image with reflection as input, and then separates the input image into the background and reflection layers. The second stage involves a refinement network to recover the missing details of the background layers. We simulate different types of user guidance, and the networks are trained on simulated data. The cascaded networks are end-to-end and perform with a single feed-forward pass, enabling fast editing. Extensive experimental evaluations demonstrate that the proposed used-guided reflection removal network yields better performance than the state-of-the-art methods on real-world scenarios. Furthermore, we show that novice users can easily generate reflection-free images, and large improvements in reflection removal quality can be obtained in just one minute.

I. Introduction

Undesired reflections of a photo taken in front of a glass often ruin the picture. To remove reflection artifacts, it is impractical to condition the imaging environment (e.g., use polarizers), so using a computational approach is usually preferred. An image containing reflections is a non-linear combination of two layers, the background and reflection layers. Therefore, removing reflection artifacts from the input image is equivalent to decompose the image into two layers. This problem, however, is obviously ill-posed as there will be an infinite number of valid decompositions.