Location-aware Single Image Reflection Removal

TL;DR

This paper introduces a location-aware deep learning method for single image reflection removal that uses a probabilistic reflection confidence map and Laplacian features to improve boundary detection and result quality.

Contribution

It presents a novel recurrent network with a reflection detection module leveraging Laplacian features, significantly enhancing reflection removal performance.

Findings

Outperforms state-of-the-art methods in reflection removal quality

Uses Laplacian features to emphasize reflection boundaries

Employs a probabilistic confidence map for better region classification

Abstract

This paper proposes a novel location-aware deep-learning-based single image reflection removal method. Our network has a reflection detection module to regress a probabilistic reflection confidence map, taking multi-scale Laplacian features as inputs. This probabilistic map tells if a region is reflection-dominated or transmission-dominated, and it is used as a cue for the network to control the feature flow when predicting the reflection and transmission layers. We design our network as a recurrent network to progressively refine reflection removal results at each iteration. The novelty is that we leverage Laplacian kernel parameters to emphasize the boundaries of strong reflections. It is beneficial to strong reflection detection and substantially improves the quality of reflection removal results. Extensive experiments verify the superior performance of the proposed method over state-of-the-art approaches. Our code and the pre-trained model can be found at https://github.com/zdlarr/Location-aware-SIRR.