Mirror, Mirror, on the Wall, Who's Got the Clearest Image of Them All? - A Tailored Approach to Single Image Reflection Removal

TL;DR

This paper presents a novel optimization-based method for single image reflection removal that incorporates user interaction and an $H^2$ fidelity term, outperforming existing techniques and competing with deep-learning approaches.

Contribution

It introduces a new optimization framework with user interaction and an $H^2$ fidelity term for improved reflection removal in single images.

Findings

Outperforms state-of-the-art reflection removal methods

Preserves fine details and global color consistency

Competes effectively with recent deep-learning approaches

Abstract

Removing reflection artefacts from a single image is a problem of both theoretical and practical interest, which still presents challenges because of the massively ill-posed nature of the problem. In this work, we propose a technique based on a novel optimisation problem. Firstly, we introduce a simple user interaction scheme, which helps minimise information loss in reflection-free regions. Secondly, we introduce an $H^2$ fidelity term, which preserves fine detail while enforcing global colour similarity. We show that this combination allows us to mitigate some major drawbacks of the existing methods for reflection removal. We demonstrate, through numerical and visual experiments, that our method is able to outperform the state-of-the-art methods and compete with recent deep-learning approaches.