Zhang, KaihaoLuo, WenhanZhong, YiranMa, LinStenger, BjornLiu, WeiLi, Hongdong2025-05-232025-05-231063-6919ORCID:/0000-0003-4125-1554/work/163239714http://www.scopus.com/inward/record.url?scp=85094860744&partnerID=8YFLogxKhttps://hdl.handle.net/1885/733753173Existing deep learning methods for image deblurring typically train models using pairs of sharp images and their blurred counterparts. However, synthetically blurring images does not necessarily model the blurring process in real-world scenarios with sufficient accuracy. To address this problem, we propose a new method which combines two GAN models, i.e., a learning-to-Blur GAN (BGAN) and learning-to-DeBlur GAN (DBGAN), in order to learn a better model for image deblurring by primarily learning how to blur images. The first model, BGAN, learns how to blur sharp images with unpaired sharp and blurry image sets, and then guides the second model, DBGAN, to learn how to correctly deblur such images. In order to reduce the discrepancy between real blur and synthesized blur, a relativistic blur loss is leveraged. As an additional contribution, this paper also introduces a Real-World Blurred Image (RWBI) dataset including diverse blurry images. Our experiments show that the proposed method achieves consistently superior quantitative performance as well as higher perceptual quality on both the newly proposed dataset and the public GOPRO dataset.This work is funded in part by the ARC Centre of Excellence for Robotics Vision (CE140100016), ARC-Discovery (DP 190102261) and ARC-LIEF (190100080) grants, as well as a research grant from Baidu on autonomous driving. The authors gratefully acknowledge the GPUs donated by NVIDIA Corporation. This work is funded in part by the ARC Centre of Excellence for Robotics Vision (CE140100016), ARC-Discovery (DP 190102261) and ARC-LIEF (190100080) grants, as well as a research grant from Baidu on autonomous driving. The authors gratefully acknowledge the GPUs donated by NVIDIA Corporation. We thank all anonymous reviewers and ACs for their constructive comments.10enPublisher Copyright: © 2020 IEEE.202010.1109/CVPR42600.2020.0028185094860744