Benchmarking single-image reflection removal algorithms

Renjie Wan, Boxin Shi*, Haoliang Li, Yuchen Hong, Lingyu Duan, Alex C. Kot

*Corresponding author for this work

Research output: Contribution to journalJournal articlepeer-review

10 Citations (Scopus)

Abstract

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 “SIR2+ ” 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/.
Original languageEnglish
Pages (from-to)1424 - 1441
Number of pages18
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Volume45
Issue number2
Early online date19 Apr 2022
DOIs
Publication statusPublished - 1 Feb 2023

Scopus Subject Areas

  • Software
  • Computer Vision and Pattern Recognition
  • Computational Theory and Mathematics
  • Artificial Intelligence
  • Applied Mathematics

User-Defined Keywords

  • Reflection removal
  • benchmark dataset
  • deep learning

Fingerprint

Dive into the research topics of 'Benchmarking single-image reflection removal algorithms'. Together they form a unique fingerprint.

Cite this