A Comprehensive Benchmark Analysis of Single Image Deraining: Current Challenges and Future Perspectives

Autor(es)

Li, Siyuan ^[1] ; Ren, Wenqi ^[2] ; Wang, Feng ^[1] ; Araujo, Iago Breno ^[3] ; Tokuda, Eric K. ^[3] ; Junior, Roberto Hirata ^[3] ; Cesar-Jr., Roberto M. ; Wang, Zhangyang ^[4] ; Cao, Xiaochun ^{[2, 5, 6]}

Afiliação do(s) autor(es)

^[1] Tianjin Univ, Coll Intelligence & Comp, Tianjin 300350 - Peoples R China

^[2] Chinese Acad Sci, Inst Informat Engn, Beijing 100093 - Peoples R China

^[3] Inst Math & Stat IME, Sao Paulo - Brazil

^[4] Univ Texas Austin, Dept Elect & Comp Engn, Austin, TX 78712 - USA

^[5] Univ Chinese Acad Sci, Sch Cyber Secur, Beijing 100049 - Peoples R China

^[6] Peng Cheng Lab, Cyberspace Secur Res Ctr, Shenzhen 518055 - Peoples R China

• Tipo de documento: Artigo Científico
• Fonte: INTERNATIONAL JOURNAL OF COMPUTER VISION; v. 129, n. 4, p. 1301-1322, APR 2021.
• Citações Web of Science: 10

Resumo

The capability of image deraining is a highly desirable component of intelligent decision-making in autonomous driving and outdoor surveillance systems. Image deraining aims to restore the clean scene from the degraded image captured in a rainy day. Although numerous single image deraining algorithms have been recently proposed, these algorithms are mainly evaluated using certain type of synthetic images, assuming a specific rain model, plus a few real images. It remains unclear how these algorithms would perform on rainy images acquired ``in the wild{''} and how we could gauge the progress in the field. This paper aims to bridge this gap. We present a comprehensive study and evaluation of existing single image deraining algorithms, using a new large-scale benchmark consisting of both synthetic and real-world rainy images of various rain types. This dataset highlights diverse rain models (rain streak, rain drop, rain and mist), as well as a rich variety of evaluation criteria (full- and no-reference objective, subjective, and task-specific). We further provide a comprehensive suite of criteria for deraining algorithm evaluation, including full- and no-reference metrics, subjective evaluation, and the novel task-driven evaluation. The proposed benchmark is accompanied with extensive experimental results that facilitate the assessment of the state-of-the-arts on a quantitative basis. Our evaluation and analysis indicate the gap between the achievable performance on synthetic rainy images and the practical demand on real-world images. We show that, despite many advances, image deraining is still a largely open problem. The paper is concluded by summarizing our general observations, identifying open research challenges and pointing out future directions. Our code and dataset is publicly available at . (AU)

• Processo FAPESP: 15/22308-2 - Representações intermediárias em Ciência Computacional para descoberta de conhecimento
• Beneficiário: Roberto Marcondes Cesar Junior
• Modalidade de apoio: Auxílio à Pesquisa - Temático