# Single Image Reflection Removal Exploiting Misaligned Training Data and Network Enhancements

## TL;DR

This paper presents a novel approach for single image reflection removal that combines network enhancements with an alignment-invariant loss to effectively utilize misaligned training data, improving performance in real-world scenarios.

## Contribution

It introduces context encoding modules for better reflection area understanding and an alignment-invariant loss to leverage misaligned data, advancing reflection removal techniques.

## Key findings

- Outperforms state-of-the-art methods with aligned data
- Significant improvements using misaligned training data
- Effective handling of real-world reflection removal scenarios

## Abstract

Removing undesirable reflections from a single image captured through a glass window is of practical importance to visual computing systems. Although state-of-the-art methods can obtain decent results in certain situations, performance declines significantly when tackling more general real-world cases. These failures stem from the intrinsic difficulty of single image reflection removal -- the fundamental ill-posedness of the problem, and the insufficiency of densely-labeled training data needed for resolving this ambiguity within learning-based neural network pipelines. In this paper, we address these issues by exploiting targeted network enhancements and the novel use of misaligned data. For the former, we augment a baseline network architecture by embedding context encoding modules that are capable of leveraging high-level contextual clues to reduce indeterminacy within areas containing strong reflections. For the latter, we introduce an alignment-invariant loss function that facilitates exploiting misaligned real-world training data that is much easier to collect. Experimental results collectively show that our method outperforms the state-of-the-art with aligned data, and that significant improvements are possible when using additional misaligned data.