Benchmarking Single-Image Reflection Removal Algorithms

• Published in: IEEE transactions on pattern analysis and machine intelligence Vol. 45; no. 2; pp. 1424 - 1441
• Main Authors: Wan, Renjie, Shi, Boxin, Li, Haoliang, Hong, Yuchen, Duan, Ling-Yu, Kot, Alex C.
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.02.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; benchmark dataset; Benchmark testing; Benchmarks; Cameras; Datasets; Deep learning; Glass; Image quality; Mathematical models; Reflection; Reflection removal; Reflectivity; State-of-the-art reviews; Taxonomy
• ISSN: 0162-8828; 1939-3539; 2160-9292; 1939-3539
• DOI: 10.1109/TPAMI.2022.3168560

Reflection removal has been discussed for more than decades. This paper aims to provide the analysis for different reflection properties and factors that influence image formation, an up-to-date taxonomy for existing methods, a benchmark dataset, and the unified benchmarking evaluations for state-of-the-art (especially learning-based) methods. Specifically, this paper presents a SIngle-image Reflection Removal Plus dataset "SIR<inline-formula><tex-math notation="LaTeX">^{2+}</tex-math> <mml:math><mml:msup><mml:mrow/><mml:mrow><mml:mn>2</mml:mn><mml:mo>+</mml:mo></mml:mrow></mml:msup></mml:math><inline-graphic xlink:href="wan-ieq1-3168560.gif"/> </inline-formula> " with the new consideration for in-the-wild scenarios and glass with diverse color and unplanar shapes. We further perform quantitative and visual quality comparisons for state-of-the-art single-image reflection removal algorithms. Open problems for improving reflection removal algorithms are discussed at the end. Our dataset and follow-up update can be found at https://reflectionremoval.github.io/sir2data/ .