Deblurring by Realistic Blurring

By Kaihao Zhang, Wenhan Luo, Yiran Zhong, Lin Ma, B. Stenger, Wei David Liu, Hongdong Li. Computer Vision and Pattern Recognition, 2020

476 citations recorded by the source corpus.

Existing 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.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/13878588e7bb424b8809cc8ffebbbc403d26ddfc

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Deep Generalized Unfolding Networks for Image Restoration (2022, methodology): “We compare our method with several competitive works [50, 61, 80, 90] and the recent best algorithm MPRNet [79].”
Uformer: A General U-Shaped Transformer for Image Restoration (2021, unknown): “[64], DeblurGAN-v2 [28], DB-GAN [77], SPAIR [44], Zhang et al .”
Ultra-High-Definition Low-Light Image Enhancement: A Benchmark and Transformer-Based Method (2022, methodology): “Data-driven methods (Wei et al. 2018; Zhang et al. 2020; Lim and Kim 2020; Ni et al. 2020; Zeng et al. 2020; Wang et al. 2022a, 2021; Yang et al. 2022) have been successfully applied to the LLIE task.”
Pre-Trained Image Processing Transformer (2020, background): “81 DBGAN [86] MTRNN [57] RADN [58] SAPHN [64] BANET [69] MB2D [56] IPT (Ours) IPT (Ours)”
Deep Image Deblurring: A Survey (2022, methodology): “Alternatively, one can train a blurringnetwork to directly generate realistically blurred images (Chen et al. 2018; Zhang et al. 2020).”
Image Restoration with Mean-Reverting Stochastic Differential Equations (2023, methodology): “For comparison, we report four milestone deblur-ring approaches: DeepDeblur (Nah et al., 2017), Deblur-GAN (Kupyn et al., 2018), DeblurGAN-v2 (Kupyn et al., 2019), DBGAN (Zhang et al., 2020), and MAXIM (Tu et al., 2022).”
Multi-Stage Progressive Image Restoration (2021, background): “Numerous network modules and functional units for image restoration have been developed including recursive residual learning [4, 95], dilated convolutions [4, 81], attention mechanisms [17, 86, 96], dense connections [73, 75, 97], encoder-decoders [7, 13, 43, 65], and generative models [44, 62, 90,”
Stripformer: Strip Transformer for Fast Image Deblurring (2022, methodology): “Qualitative comparisons on the RWBI [39].”