MC-Blur: A Comprehensive Benchmark for Image Deblurring

• Published in: IEEE transactions on circuits and systems for video technology Vol. 34; no. 5; pp. 3755 - 3767
• Main Authors: Zhang, Kaihao, Wang, Tao, Luo, Wenhan, Ren, Wenqi, Stenger, Bjorn, Liu, Wei, Li, Hongdong, Yang, Ming-Hsuan
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.05.2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Benchmark testing; Benchmarks; Cameras; Datasets; Deblurring benchmark; defocus deblur; High definition; High speed cameras; Image quality; Image restoration; large-scale multi-cause dataset; motion deblur; Performance evaluation; Quality assessment; real-world deblur; Training; UHD deblur; Videos
• ISSN: 1051-8215; 1558-2205
• DOI: 10.1109/TCSVT.2023.3319330

Blur artifacts can seriously degrade the visual quality of images, and numerous deblurring methods have been proposed for specific scenarios. However, in most real-world images, blur is caused by different factors, e.g., motion, and defocus. In this paper, we address how other deblurring methods perform in the case of multiple types of blur. For in-depth performance evaluation, we construct a new large-scale multi-cause image deblurring dataset (MC-Blur), including real-world and synthesized blurry images with different blur factors. The images in the proposed MC-Blur dataset are collected using other techniques: averaging sharp images captured by a 1000-fps high-speed camera, convolving Ultra-High-Definition (UHD) sharp images with large-size kernels, adding defocus to images, and real-world blurry images captured by various camera models. Based on the MC-Blur dataset, we conduct extensive benchmarking studies to compare SOTA methods in different scenarios, analyze their efficiency, and investigate the buildataset's capacity. These benchmarking results provide a comprehensive overview of the advantages and limitations of current deblurring methods, revealing our dataset's advances. The dataset is available to the public at https://github.com/HDCVLab/MC-Blur-Dataset .