Reflection Separation Using Guided Annotation

TL;DR

This paper introduces a novel reflection separation method that leverages a Gaussian Mixture Model patch prior, enabling automatic layer decomposition with minimal user input, especially effective for textured images.

Contribution

The paper presents a new approach using a Gaussian Mixture Model prior to facilitate reflection separation with sparse user annotations, overcoming limitations of previous sparsity-based methods.

Findings

Effective decomposition on both synthetic and real images.

Requires minimal user input for accurate separation.

Outperforms previous annotation-based methods in textured scenarios.

Abstract

Photographs taken through a glass surface often contain an approximately linear superposition of reflected and transmitted layers. Decomposing an image into these layers is generally an ill-posed task and the use of an additional image prior and user provided cues is presently necessary in order to obtain good results. Current annotation approaches rely on a strong sparsity assumption. For images with significant texture this assumption does not typically hold, thus rendering the annotation process unviable. In this paper we show that using a Gaussian Mixture Model patch prior, the correct local decomposition can almost always be found as one of 100 likely modes of the posterior. Thus, the user need only choose one of these modes in a sparse set of patches and the decomposition may then be completed automatically. We demonstrate the performance of our method using synthesized and real reflection images.