More Web Proxy on the site http://driver.im/

Article

Real-World Blur Dataset for Learning and Benchmarking Deblurring Algorithms

Authors:

Sunghyun ChoAuthors Info & Claims

Computer Vision – ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XXV

Pages 184 - 201

https://doi.org/10.1007/978-3-030-58595-2_12

Published: 23 August 2020 Publication History

Abstract

Numerous learning-based approaches to single image deblurring for camera and object motion blurs have recently been proposed. To generalize such approaches to real-world blurs, large datasets of real blurred images and their ground truth sharp images are essential. However, there are still no such datasets, thus all the existing approaches resort to synthetic ones, which leads to the failure of deblurring real-world images. In this work, we present a large-scale dataset of real-world blurred images and ground truth sharp images for learning and benchmarking single image deblurring methods. To collect our dataset, we build an image acquisition system to simultaneously capture geometrically aligned pairs of blurred and sharp images, and develop a postprocessing method to produce high-quality ground truth images. We analyze the effect of our postprocessing method and the performance of existing deblurring methods. Our analysis shows that our dataset significantly improves deblurring quality for real-world blurred images.

References

[1]

Abdelhamed, A., Lin, S., Brown, M.S.: A high-quality denoising dataset for smartphone cameras. In: CVPR, June 2018

[2]

Ben-Ezra, M., Nayar, S.: Motion deblurring using hybrid imaging. In: CVPR, pp. 657–664 (2003)

[3]

Cai, J., Zeng, H., Yong, H., Cao, Z., Zhang, L.: Toward real-world single image super-resolution: a new benchmark and a new model. In: ICCV, October 2019

[4]

Chakrabarti A Leibe B, Matas J, Sebe N, and Welling M A neural approach to blind motion deblurring Computer Vision – ECCV 2016 2016 Cham Springer 221-235

[5]

Chen, G., Zhu, F., Ann Heng, P.: An efficient statistical method for image noise level estimation. In: ICCV, December 2015

[6]

Cho, S., Lee, S.: Convergence analysis of map based blur kernel estimation. In: ICCV, pp. 4818–4826, October 2017

[7]

Cho S and Lee S Fast motion deblurring ACM Trans. Graph. 2009 28 5 145:1-145:8

[8]

Cho, S., Wang, J., Lee, S.: Handling outliers in non-blind image deconvolution. In: ICCV (2011)

[9]

Cho, T.S., Paris, S., Horn, B.K.P., Freeman, W.T.: Blur kernel estimation using the radon transform. In: CVPR (2011)

[10]

Dabov K, Foi A, Katkovnik V, and Egiazarian K Image denoising by sparse 3-D transform-domain collaborative filtering TIP 2007 16 8 2080-2095

[11]

Evangelidis GD and Psarakis EZ Parametric image alignment using enhanced correlation coefficient maximization TPAMI 2008 30 10 1858-1865

[12]

Fergus R, Singh B, Hertzmann A, Roweis ST, and Freeman WT Removing camera shake from a single photograph ACM Trans. Graph. 2006 25 3 787-794

[13]

Goodfellow, I., et al.: Generative adversarial nets. In: Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N.D., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems 27, pp. 2672–2680. Curran Associates, Inc. (2014). http://papers.nips.cc/paper/5423-generative-adversarial-nets.pdf

[14]

Gupta A, Joshi N, Lawrence Zitnick C, Cohen M, and Curless B Daniilidis K, Maragos P, and Paragios N Single image deblurring using motion density functions Computer Vision – ECCV 2010 2010 Heidelberg Springer 171-184

[15]

Heikkila, J., Silven, O.: A four-step camera calibration procedure with implicit image correction. In: CVPR, CVPR 1997, p. 1106. IEEE Computer Society, USA (1997)

[16]

Hirakawa K and Parks TW Adaptive homogeneity-directed demosaicing algorithm TIP 2005 14 3 360-369

[17]

Hirsch, M., Schuler, C.J., Harmeling, S., Schölkopf, B.: Fast removal of non-uniform camera shake. In: ICCV, pp. 463–470 (2011)

[18]

Hu Z, Cho S, Wang J, and Yang M Deblurring low-light images with light streaks IEEE Trans. Pattern Anal. Mach. Intell. 2018 40 10 2329-2341

[19]

Kim, T.H., Lee, K.M.: Segmentation-free dynamic scene deblurring. In: CVPR, pp. 2766–2773, June 2014

[20]

Köhler R, Hirsch M, Mohler B, Schölkopf B, and Harmeling S Fitzgibbon A, Lazebnik S, Perona P, Sato Y, and Schmid C Recording and playback of camera shake: benchmarking blind deconvolution with a real-world database Computer Vision – ECCV 2012 2012 Heidelberg Springer 27-40

[21]

Kupyn, O., Budzan, V., Mykhailych, M., Mishkin, D., Matas, J.: DeblurGAN: blind motion deblurring using conditional adversarial networks. In: CVPR, June 2018

[22]

Kupyn, O., Martyniuk, T., Wu, J., Wang, Z.: DeblurGAN-v2: deblurring (orders-of-magnitude) faster and better. In: ICCV, October 2019

[23]

Lai, W.S., Huang, J.B., Hu, Z., Ahuja, N., Yang, M.H.: A comparative study for single image blind deblurring. In: CVPR, June 2016

[24]

Levin, A., Weiss, Y., Durand, F., Freeman, W.T.: Understanding and evaluating blind deconvolution algorithms. In: CVPR, pp. 1964–1971 (2009)

[25]

Levin, A., Weiss, Y., Durand, F., Freeman, W.T.: Efficient marginal likelihood optimization in blind deconvolution. In: CVPR, pp. 2657–2664 (2011)

[26]

Li, F., Yu, J., Chai, J.: A hybrid camera for motion deblurring and depth map super-resolution. In: CVPR (2008)

[27]

Lu, B., Chen, J.C., Chellappa, R.: Unsupervised domain-specific deblurring via disentangled representations. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2019

[28]

Madam NT, Kumar S, and Rajagopalan AN Ferrari V, Hebert M, Sminchisescu C, and Weiss Y Unsupervised class-specific deblurring Computer Vision – ECCV 2018 2018 Cham Springer 358-374

[29]

Martin, D., Fowlkes, C., Tal, D., Malik, J.: A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In: ICCV, vol. 2, pp. 416–423 (2001)

[30]

Nah, S., et al.: NTIRE 2019 challenge on video deblurring and super-resolution: dataset and study. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, June 2019

[31]

Nah, S., Hyun Kim, T., Mu Lee, K.: Deep multi-scale convolutional neural network for dynamic scene deblurring. In: CVPR, July 2017

[32]

Noroozi M, Chandramouli P, and Favaro P Roth V and Vetter T Motion deblurring in the wild Pattern Recognition 2017 Cham Springer 65-77

[33]

Pan, J., Sun, D., Pfister, H., Yang, M.H.: Blind image deblurring using dark channel prior. In: CVPR, pp. 1628–1636 (2016)

[34]

Plotz, T., Roth, S.: Benchmarking denoising algorithms with real photographs. In: CVPR, July 2017

[35]

Reddy BS and Chatterji BN An FFT-based technique for translation, rotation, and scale-invariant image registration TIP 1996 5 8 1266-1271

[36]

Schmidt U, Jancsary J, Nowozin S, Roth S, and Rother C Cascades of regression tree fields for image restoration TPAMI 2016 38 4 677-689

[37]

Schuler CJ, Hirsch M, Harmeling S, and Schölkopf B Learning to deblur TPAMI 2016 38 7 1439-1451

[38]

Shan Q, Jia J, and Agarwala A High-quality motion deblurring from a single image ACM Trans. Graph. 2008 27 3 73:1-73:10

[39]

Su, S., Delbracio, M., Wang, J., Sapiro, G., Heidrich, W., Wang, O.: Deep video deblurring for hand-held cameras. In: CVPR, pp. 237–246, July 2017

[40]

Sun, L., Cho, S., Wang, J., Hays, J.: Edge-based blur kernel estimation using patch priors. In: ICCP (2013)

[41]

Tai, Y.W., Du, H., Brown, M.S., Lin, S.: Image/video deblurring using a hybrid camera. In: CVPR (2008)

[42]

Tao, X., Gao, H., Shen, X., Wang, J., Jia, J.: Scale-recurrent network for deep image deblurring. In: CVPR, June 2018

[43]

Wang Z, Bovik AC, Sheikh HR, and Simoncelli EP Image quality assessment: from error visibility to structural similarity TIP 2004 13 4 600-612

[44]

Whyte, O., Sivic, J., Zisserman, A., Ponce, J.: Non-uniform deblurring for shaken images. In: CVPR, pp. 491–498 (2010)

[45]

Xu L and Jia J Daniilidis K, Maragos P, and Paragios N Two-phase kernel estimation for robust motion deblurring Computer Vision – ECCV 2010 2010 Heidelberg Springer 157-170

[46]

Xu, L., Zheng, S., Jia, J.: Unnatural L0 sparse representation for natural image deblurring. In: CVPR (2013)

[47]

Yuan, L., Sun, J., Quan, L., Shum, H.: Image deblurring with blurred/noisy image pairs. In: SIGGRAPH (2007)

[48]

Zhang, H., Dai, Y., Li, H., Koniusz, P.: Deep stacked hierarchical multi-patch network for image deblurring. In: CVPR, June 2019

[49]

Zhang, J., et al.: Dynamic scene deblurring using spatially variant recurrent neural networks. In: CVPR, June 2018

[50]

Zhang Z A flexible new technique for camera calibration TPAMI 2000 22 11 1330-1334

[51]

Zhou, S., Zhang, J., Zuo, W., Xie, H., Pan, J., Ren, J.S.: DAVANet: stereo deblurring with view aggregation. In: CVPR, pp. 10988–10997, June 2019

[52]

Šorel, M., Šroubek, F.: Space-variant deblurring using one blurred and one underexposed image. In: ICIP, pp. 157–160 (2009)

Cited By

Zhang YCai YYan DLin R(2024)Real-World Scene Image Enhancement with Contrastive Domain Adaptation LearningACM Transactions on Multimedia Computing, Communications, and Applications10.1145/369497320:12(1-23)Online publication date: 26-Nov-2024
https://dl.acm.org/doi/10.1145/3694973
Xiao ZLu ZBi Mi MXiong ZWang XCai JKankanhalli MPrabhakaran BBoll SSubramanian RZheng LSingh VCesar PXie LXu D(2024)Unraveling Motion Uncertainty for Local Motion DeblurringProceedings of the 32nd ACM International Conference on Multimedia10.1145/3664647.3681239(3065-3074)Online publication date: 28-Oct-2024
https://dl.acm.org/doi/10.1145/3664647.3681239
Ma YDuan PHong YZhou CZhang YRen JShi BCai JKankanhalli MPrabhakaran BBoll SSubramanian RZheng LSingh VCesar PXie LXu D(2024)Color4E: Event Demosaicing for Full-color Event Guided Image DeblurringProceedings of the 32nd ACM International Conference on Multimedia10.1145/3664647.3681051(661-670)Online publication date: 28-Oct-2024
https://dl.acm.org/doi/10.1145/3664647.3681051
Show More Cited By

Index Terms

Real-World Blur Dataset for Learning and Benchmarking Deblurring Algorithms
1. Computing methodologies

Index terms have been assigned to the content through auto-classification.

Recommendations

Joint learning of motion deblurring and defocus deblurring networks with a real-world dataset
Abstract
When recovering the sharp image from a blurry observation, moving objects, e.g., people and vehicles, usually attract more perceptual attention. However, existing motion deblurring methods primarily focus on removing the global camera motion blur,...
United Defocus Blur Detection and Deblurring via Adversarial Promoting Learning
Computer Vision – ECCV 2022
Abstract
Understanding blur from a single defocused image contains two tasks of defocus detection and deblurring. This paper makes the earliest effort to jointly learn both defocus detection and deblurring without using pixel-level defocus detection ... $_{}$ $_{}$ $_{}$ $_{}$ $_{}$ $_{}$ $_{}$ $_{}$ $_{}$ $_{}$ $_{}$
Spatially variant defocus blur map estimation and deblurring from a single image

A blur map estimation method using edge information is proposed.The blur map is segmented into multiple superpixels according to the image contours.Ringing artifacts and noise are detected and removed after deconvolution. In this paper, we propose a ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image Guide Proceedings

Computer Vision – ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XXV

Aug 2020

829 pages

ISBN:978-3-030-58594-5

DOI:10.1007/978-3-030-58595-2

Editors:
Andrea Vedaldi
University of Oxford, Oxford, UK
,
Horst Bischof
Graz University of Technology, Graz, Austria
,
Thomas Brox
University of Freiburg, Freiburg im Breisgau, Germany
,
Jan-Michael Frahm
University of North Carolina at Chapel Hill, Chapel Hill, NC, USA

© Springer Nature Switzerland AG 2020.

Publisher

Springer-Verlag

Berlin, Heidelberg

Publication History

Published: 23 August 2020

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

35
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 05 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

Zhang YCai YYan DLin R(2024)Real-World Scene Image Enhancement with Contrastive Domain Adaptation LearningACM Transactions on Multimedia Computing, Communications, and Applications10.1145/369497320:12(1-23)Online publication date: 26-Nov-2024
https://dl.acm.org/doi/10.1145/3694973
Xiao ZLu ZBi Mi MXiong ZWang XCai JKankanhalli MPrabhakaran BBoll SSubramanian RZheng LSingh VCesar PXie LXu D(2024)Unraveling Motion Uncertainty for Local Motion DeblurringProceedings of the 32nd ACM International Conference on Multimedia10.1145/3664647.3681239(3065-3074)Online publication date: 28-Oct-2024
https://dl.acm.org/doi/10.1145/3664647.3681239
Ma YDuan PHong YZhou CZhang YRen JShi BCai JKankanhalli MPrabhakaran BBoll SSubramanian RZheng LSingh VCesar PXie LXu D(2024)Color4E: Event Demosaicing for Full-color Event Guided Image DeblurringProceedings of the 32nd ACM International Conference on Multimedia10.1145/3664647.3681051(661-670)Online publication date: 28-Oct-2024
https://dl.acm.org/doi/10.1145/3664647.3681051
Mao XWang JXie XLi QWang YCai JKankanhalli MPrabhakaran BBoll SSubramanian RZheng LSingh VCesar PXie LXu D(2024)LoFormer: Local Frequency Transformer for Image DeblurringProceedings of the 32nd ACM International Conference on Multimedia10.1145/3664647.3680888(10382-10391)Online publication date: 28-Oct-2024
https://dl.acm.org/doi/10.1145/3664647.3680888
Gao HMa BZhang YYang JYang JDang DCai JKankanhalli MPrabhakaran BBoll SSubramanian RZheng LSingh VCesar PXie LXu D(2024)Learning Enriched Features via Selective State Spaces Model for Efficient Image DeblurringProceedings of the 32nd ACM International Conference on Multimedia10.1145/3664647.3680624(710-718)Online publication date: 28-Oct-2024
https://dl.acm.org/doi/10.1145/3664647.3680624
Zhang YZhang JFu XJiang NLi Q(2024)Dynamic scene deblurring via receptive field attention generative adversarial networkComputers and Graphics10.1016/j.cag.2023.09.004116:C(354-362)Online publication date: 4-Mar-2024
https://dl.acm.org/doi/10.1016/j.cag.2023.09.004
Zhuang ZLi TWang HSun J(2024)Blind Image Deblurring with Unknown Kernel Size and Substantial NoiseInternational Journal of Computer Vision10.1007/s11263-023-01883-x132:2(319-348)Online publication date: 1-Feb-2024
https://dl.acm.org/doi/10.1007/s11263-023-01883-x
Liao JPeng CJiang LMa YLiang WLi KPoniszewska-Maranda A(2024)MWformer: a novel low computational cost image restoration algorithmThe Journal of Supercomputing10.1007/s11227-024-06160-380:14(21508-21532)Online publication date: 12-Jun-2024
https://dl.acm.org/doi/10.1007/s11227-024-06160-3
He JTsai FWu JPeng YTsai CLin CLin Y(2024)Domain-Adaptive Video Deblurring via Test-Time BlurringComputer Vision – ECCV 202410.1007/978-3-031-73404-5_8(125-142)Online publication date: 29-Sep-2024
https://dl.acm.org/doi/10.1007/978-3-031-73404-5_8
Kim TJeong JCho HJeong YYoon K(2024)Towards Real-World Event-Guided Low-Light Video Enhancement and DeblurringComputer Vision – ECCV 202410.1007/978-3-031-73254-6_25(433-451)Online publication date: 29-Sep-2024
https://dl.acm.org/doi/10.1007/978-3-031-73254-6_25
Show More Cited By

View Options

View options

Media

Figures

Other

Tables

View Table of Contents