Survey on Single-Image Reflection Removal using Deep Learning Techniques

TL;DR

This survey addresses the problem of single-image reflection removal (SIRR), an ill-posed task of recovering the transmission image $T$ from a reflected scene concealed in $I$. It emphasizes deep learning approaches across single-stage, two-stage, and multi-stage architectures, detailing modeling hypotheses, loss functions, and learning objectives. The review systematically covers data acquisition, public datasets, and evaluation metrics, and identifies key challenges such as data scarcity and inconsistent task definitions, offering concrete future directions including large-scale datasets and multimodal cues. The work aims to guide researchers and practitioners by consolidating recent advances, outlining opportunities, and proposing a path toward more reliable and generalizable SIRR solutions.

Abstract

The phenomenon of reflection is quite common in digital images, posing significant challenges for various applications such as computer vision, photography, and image processing. Traditional methods for reflection removal often struggle to achieve clean results while maintaining high fidelity and robustness, particularly in real-world scenarios. Over the past few decades, numerous deep learning-based approaches for reflection removal have emerged, yielding impressive results. In this survey, we conduct a comprehensive review of the current literature by focusing on key venues such as ICCV, ECCV, CVPR, NeurIPS, etc., as these conferences and journals have been central to advances in the field. Our review follows a structured paper selection process, and we critically assess both single-stage and two-stage deep learning methods for reflection removal. The contribution of this survey is three-fold: first, we provide a comprehensive summary of the most recent work on single-image reflection removal; second, we outline task hypotheses, current deep learning techniques, publicly available datasets, and relevant evaluation metrics; and third, we identify key challenges and opportunities in deep learning-based reflection removal, highlighting the potential of this rapidly evolving research area.