Learned Dual-View Reflection Removal

TL;DR

This paper introduces a learning-based dual-view reflection removal method using stereo images, effectively leveraging parallax cues and easy capture with smartphones to outperform existing approaches.

Contribution

It proposes a novel stereo image-based reflection removal algorithm with a new synthetic dataset, addressing limitations of single and multi-image methods.

Findings

Outperforms existing single-image and multi-image reflection removal methods.

Uses a synthetic dataset for training due to lack of real dual-view reflection datasets.

Demonstrates effectiveness on real-world stereo image pairs.

Abstract

Traditional reflection removal algorithms either use a single image as input, which suffers from intrinsic ambiguities, or use multiple images from a moving camera, which is inconvenient for users. We instead propose a learning-based dereflection algorithm that uses stereo images as input. This is an effective trade-off between the two extremes: the parallax between two views provides cues to remove reflections, and two views are easy to capture due to the adoption of stereo cameras in smartphones. Our model consists of a learning-based reflection-invariant flow model for dual-view registration, and a learned synthesis model for combining aligned image pairs. Because no dataset for dual-view reflection removal exists, we render a synthetic dataset of dual-views with and without reflections for use in training. Our evaluation on an additional real-world dataset of stereo pairs shows that our algorithm outperforms existing single-image and multi-image dereflection approaches.