Attentive Generative Adversarial Network for Raindrop Removal from A Single Image
Open accessAbstract
Raindrops adhered to a glass window or camera lens can severely hamper the visibility of a background scene and degrade an image considerably. In this paper, we address the problem by visually removing raindrops, and thus transforming a raindrop degraded image into a clean one. The problem is intractable, since first the regions occluded by raindrops are not given. Second, the information about the background scene of the occluded regions is completely lost for most part. To resolve the problem, we apply an attentive generative network using adversarial training. Our main idea is to inject visual attention into both the generative and discriminative networks. During the training, our visual attention learns about raindrop regions and their surroundings. Hence, by injecting this information, the generative network will pay more attention to the raindrop regions and the surrounding structures, and the discriminative network will be able to assess the local consistency of the restored regions. This injection of visual attention to both generative and discriminative networks is the main contribution of this paper. Our experiments show the effectiveness of our approach, which outperforms the state of the art methods quantitatively and qualitatively.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Results show improvements in system performance with the help of attention maps (A + AD vs. A + D and A).
“Results also show the improvements in system performance with the help of attention maps (A + AD vs. A + D and A), where”
From A Review of Detection and Removal of Raindrops in Automotive Vision Systems (2021) · cites this paper as [49]
Qian et al. proposed a raindrop removal algorithm based on an attentive Generative Adversarial Network, named DeRaindrop.
“Qian et al. [49] proposed a raindrop removal algorithm, based on an attentive Generative Adversarial Network (GAN). Their implementation of this algorithm is named “DeRaindrop””
From A Review of Detection and Removal of Raindrops in Automotive Vision Systems (2021) · cites this paper as [49]
The proposed system outperformed the other systems in terms of PSNR and SSIM.
“The proposed system outperformed the other systems, both in terms of PSNR and SSIM (Structure SIMilarity index).”
From A Review of Detection and Removal of Raindrops in Automotive Vision Systems (2021) · cites this paper as [49]
Using the Qian et al. [49] dataset for training and testing, both Attentive GAN [49] and Kim et al.'s proposed algorithm improved PSNR and SSIM scores of restored images versus distorted images.
“Using Qian et al. [49] dataset for training and testing showed that both attentive GAN [49] and Kim et al. proposed algorithm improved quantitative score of PSNR and SSIM of restored image versus distorted one.”
From A Review of Detection and Removal of Raindrops in Automotive Vision Systems (2021) · cites this paper as [49]
Qualitatively, Hoa et al.'s proposed algorithm, as well as Qian's and DID-MDN, removed most raindrops successfully.
“Qualitatively, the proposed algorithm, as well as Qian’s and the DIID-MDN removed most raindrops successfully.”
From A Review of Detection and Removal of Raindrops in Automotive Vision Systems (2021) · cites this paper as [49]
Peng et al.'s proposed solution slightly outperformed Qian's algorithm, with the added value of smaller system size.
“The proposed solution also slightly outperformed Qian’s algorithm with the added value of smaller system size.”
From A Review of Detection and Removal of Raindrops in Automotive Vision Systems (2021) · cites this paper as [49]
Qian et al.'s approach made the rain-free region blurred.
“Qian et al. [49] made the rain-free region blurred.”
From A Review of Detection and Removal of Raindrops in Automotive Vision Systems (2021) · cites this paper as [49]
When trained using Qian et al.'s dataset with only a rough mask, Hoa et al.'s proposed algorithm produced results on-par with Qian and better than all other methods.
“Results showed that the proposed algorithm produced results that were on-par with Qian [49] and better than all other methods.”
From A Review of Detection and Removal of Raindrops in Automotive Vision Systems (2021) · cites this paper as [49]
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · see citing works
Image-to-Image Translation with Conditional Adversarial Networks
Isola, P., Zhu, J.-Y., Zhou, T., & Efros, A. A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.632 · Cited by 22,930 · see citing works
Labaca-Castro, R. (2023) · Springer eBooks · doi:10.1007/978-3-658-40442-0_9 · Cited by 21,099 · see citing works
GAN（Generative Adversarial Nets）
淳司, 柴. (2017) · Journal of Japan Society for Fuzzy Theory and Intelligent Informatics · doi:10.3156/jsoft.29.5_177_2 · Cited by 19,268 · see citing works
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
Johnson, J., Alahi, A., & Fei-Fei, L. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46475-6_43 · Cited by 11,283 · see citing works
Single image haze removal using dark channel prior
He, K., Sun, J., & Tang, X. (2011) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2010.168 · Cited by 7,601 · see citing works
Recurrent Models of Visual AttentionPreprint
Mnih, V., Heess, N., Graves, A., & Kavukcuoglu, K. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1406.6247 · Cited by 3,286 · see citing works
Visibility in bad weather from a single image
Tan, R. T. (2008) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2008.4587643 · Cited by 2,313 · see citing works
Self-citationGlobally and locally consistent image completion
Iizuka, S., Simo-Serra, E., & Ishikawa, H. (2017) · ACM Transactions on Graphics · doi:10.1145/3072959.3073659 · Cited by 2,203 · see citing works
Single Image Dehazing via Multi-scale Convolutional Neural Networks
Ren, W., Liu, S., Zhang, H., Pan, J., Cao, X., & Yang, M. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46475-6_10 · Cited by 1,878 · see citing works
DRAW: A Recurrent Neural Network For Image GenerationPreprint
Gregor, K., Danihelka, I., Graves, A., Rezende, D. J., & Wierstra, D. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1502.04623 · Cited by 1,394 · see citing works
Deep Joint Rain Detection and Removal from a Single Image
Yang, W., Tan, R. T., Feng, J., Liu, J., Guo, Z., & Yan, S. (2017) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2017.183 · Cited by 1,280 · see citing works
Self-citationClearing the Skies: A Deep Network Architecture for Single-Image Rain Removal
Fu, X., Huang, J., Ding, X., Liao, Y., & Paisley, J. W. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2691802 · Cited by 939 · see citing works
DRAW: A Recurrent Neural Network For Image Generation
Gregor, K., Danihelka, I., Graves, A., Rezende, D. J., & Wierstra, D. (2015) · Cited by 785 · see citing works
Li, Y., Liu, S., Yang, J., & Yang, M. (2017) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2017.624 · Cited by 659 · see citing works
Garg, K., & Nayar, S. K. (2007) · International Journal of Computer Vision · doi:10.1007/s11263-006-0028-6 · Cited by 477 · see citing works
Restoring an Image Taken through a Window Covered with Dirt or Rain
Eigen, D., Krishnan, D., & Fergus, R. (2013) · 2013 IEEE International Conference on Computer Vision · doi:10.1109/iccv.2013.84 · Cited by 454 · see citing works
Rainy weather recognition from in-vehicle camera images for driver assistance
Kurihata, H., Takahashi, T., Ide, I., Mekada, Y., Murase, H., Tamatsu, Y., & Miyahara, T. (2005) · IEEE Proceedings. Intelligent Vehicles Symposium, 2005. · doi:10.1109/ivs.2005.1505103 · Cited by 177 · see citing works
Adherent Raindrop Modeling, Detection and Removal in Video
You, S., Tan, R. T., Kawakami, R., Mukaigawa, Y., & Ikeuchi, K. (2015) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2015.2491937 · Cited by 169 · see citing works
Self-citationVideo-based raindrop detection for improved image registration
Roser, M., & Geiger, A. (2009) · 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops · doi:10.1109/iccvw.2009.5457650 · Cited by 126 · see citing works
Realistic Modeling of Water Droplets for Monocular Adherent Raindrop Recognition Using Bézier Curves
Roser, M., Kurz, J., & Geiger, A. (2011) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-22819-3_24 · Cited by 63 · see citing works
Removal of adherent waterdrops from images acquired with stereo camera
Yamashita, A., Tanaka, Y., & Kaneko, T. (2005) · 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems · doi:10.1109/iros.2005.1545103 · Cited by 55 · see citing works
Yamashita, A., Fukuchi, I., & Kaneko, T. (2009) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2009.5354639 · Cited by 33 · see citing works
Removal of Adherent Waterdrops from Images Acquired with a Stereo Camera System
Tanaka, Y. (2006) · IEICE Transactions on Information and Systems · doi:10.1093/ietisy/e89-d.7.2021 · Cited by 31 · see citing works
Removal of Glare Caused by Water Droplets
Hara, T., Saitô, H., & Kanade, T. (2009) · doi:10.1109/cvmp.2009.17 · Cited by 26 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
All in One Bad Weather Removal Using Architectural Search
Li, R., Tan, R. T., & Cheong, L.-F. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00324 · Cited by 377 · see citing works
Self-citationLearning From Synthetic Photorealistic Raindrop for Single Image Raindrop Removal
Hao, Z., You, S., Li, Y., Li, K., & Lu, F. (2019) · 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) · doi:10.1109/iccvw.2019.00534 · Cited by 54 · see citing works
Raindrops on Windshield: Dataset and Lightweight Gradient-Based Detection Algorithm
Soboleva, V., & Shipitko, O. (2021) · 2021 IEEE Symposium Series on Computational Intelligence (SSCI) · doi:10.1109/ssci50451.2021.9659915 · Cited by 30 · see citing works
A Review of Detection and Removal of Raindrops in Automotive Vision Systems
Hamzeh, Y., & Rawashdeh, S. A. (2021) · Journal of Imaging · doi:10.3390/jimaging7030052 · Cited by 21 · see citing works
“[49] dataset for training and testing showed that both attentive GAN [49] and Kim et al.”
BackgroundMethodResultInfluentialRaindrop-Aware GAN: Unsupervised Learning for Raindrop-Contaminated Coastal Video Enhancement
Kim, J., Huh, D., Kim, T., Kim, J., Yoo, J., & Shim, J.-S. (2020) · Remote Sensing · doi:10.3390/rs12203461 · Cited by 4 · see citing works
- Authors
- Qian, R., Tan, R. T., Yang, W., Su, J., & Liu, J.
- Affiliations
- Peking University (CN)
- Yale-NUS College (SG)
- Venue
- 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
- Publisher
- IEEE
- Published
- 2018-06
- Pages
- 2482-2491
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2963800716
- Cited by
- 821
- References
- 25
- Citations by year
- 2026: 69 · 2025: 118 · 2024: 118 · 2023: 92 · 2022: 129 · 2021: 133 · 2020: 101 · 2019: 51 · 2018: 10
- FWCI
- 22.23
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Yale University
- Nvidia
- Yale-NUS College
- Tencent
- National Research Foundation
- National Natural Science Foundation of China (61772043)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Enhancement Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image and Signal Denoising Methods
- Keywords
- raindrop removal, image restoration, generative adversarial networks, visual attention, occlusion, image denoising, adversarial training, image inpainting
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
