The DOI matches its Crossref record; 26 of the 27 references it cites were found in a registry or an index.
Restoring an Image Taken through a Window Covered with Dirt or Rain
Abstract
Photographs taken through a window are often compromised by dirt or rain present on the window surface. Common cases of this include pictures taken from inside a vehicle, or outdoor security cameras mounted inside a protective enclosure. At capture time, defocus can be used to remove the artifacts, but this relies on achieving a shallow depth-of-field and placement of the camera close to the window. Instead, we present a post-capture image processing solution that can remove localized rain and dirt artifacts from a single image. We collect a dataset of clean/corrupted image pairs which are then used to train a specialized form of convolutional neural network. This learns how to map corrupted image patches to clean ones, implicitly capturing the characteristic appearance of dirt and water droplets in natural images. Our models demonstrate effective removal of dirt and rain in outdoor test conditions.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
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?
In the citing paper
“The other three methods caused much degradation to non-dirt areas of the images.”
From A Review of Detection and Removal of Raindrops in Automotive Vision Systems (2021) · cites this paper as [46]
In the citing paper
“Testing with other types of sensitized noise, namely snow, and scratches on the image surface resulted in the system described by Eigen et al. producing near-zero PSNR (peak signal to noise ratio) which demonstrates that the system learned to remove dirt noise only.”
From A Review of Detection and Removal of Raindrops in Automotive Vision Systems (2021) · cites this paper as [46]
In the citing paper
“Synthesized rain that the proposed system outperformed the MLP system, in terms of removing more rain droplets and maintain non-rain areas of the image intact.”
From A Review of Detection and Removal of Raindrops in Automotive Vision Systems (2021) · cites this paper as [46]
In the citing paper
“Synthetic dirt results showed that the proposed system and the MLP system outperformed the other three baseline methods.”
From A Review of Detection and Removal of Raindrops in Automotive Vision Systems (2021) · cites this paper as [46]
In the citing paper
“Real-life dirt results showed that the proposed system removed most dirt noise in the images, while the MLP left many more unremoved.”
From A Review of Detection and Removal of Raindrops in Automotive Vision Systems (2021) · cites this paper as [46]
In the citing paper
“The proposed system failed to recognize large dirt noises and the ones that are out of shape, as well as dirt over areas that were not represented in the training set (e.g., bright orange cones).”
From A Review of Detection and Removal of Raindrops in Automotive Vision Systems (2021) · cites this paper as [46]
In the citing paper
“The median filter needed to blur the image substantially before it was able to reduce raindrops.”
From A Review of Detection and Removal of Raindrops in Automotive Vision Systems (2021) · cites this paper as [46]
In the citing paper
“Eigen et al. [46] proposed a system to remove dirt and raindrop noise from a single image, using the NN architecture originally developed by LeCun et al. [47].”
From A Review of Detection and Removal of Raindrops in Automotive Vision Systems (2021) · cites this paper as [46]
In the citing paper
“Real rain results showed that the proposed system successfully removed real raindrops from the captured images, but it started failing with the accumulation of water on the glass plate.”
From A Review of Detection and Removal of Raindrops in Automotive Vision Systems (2021) · cites this paper as [46]
Citations
Cites
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805
Bilateral Filtering for Gray and Color Images
Tomasi, C., & Manduchi, R. (2002) · Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271) · doi:10.1109/iccv.1998.710815 · Cited by 8,177 · cited 1×
“We compare our convolutional network against a nonconvolutional patch-level network similar to [2], as well as three baseline approaches: median filtering, bilateral filtering [18, 15], and BM3D [3].”
MethodSparse coding with an overcomplete basis set: A strategy employed by V1?
Olshausen, B. A., & Field, D. J. (1997) · Vision Research · doi:10.1016/s0042-6989(97)00169-7 · Cited by 3,642
Image denoising using scale mixtures of gaussians in the wavelet domain
Portilla, J., Strela, V., Wainwright, M. J., & Simoncelli, E. P. (2003) · IEEE Transactions on Image Processing · doi:10.1109/tip.2003.818640 · Cited by 2,280
From learning models of natural image patches to whole image restoration
Zoran, D., & Weiss, Y. (2011) · 2011 International Conference on Computer Vision · doi:10.1109/iccv.2011.6126278 · Cited by 1,522
Image denoising: Can plain neural networks compete with BM3D?
Burger, H. C., Schuler, C. J., & Harmeling, S. (2012) · 2012 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2012.6247952 · Cited by 1,325
Image Denoising and Inpainting with Deep Neural Networks
Xie, J., Xu, L., & Chen, E. (2012) · Cited by 1,237
(2008) · Cited by 838
A Fast Approximation of the Bilateral Filter Using a Signal Processing Approach
Paris, S., & Durand, F. (2007) · International Journal of Computer Vision · doi:10.1007/s11263-007-0110-8 · Cited by 796
Image denoising with block-matching and 3D filtering
Dabov, K., Foi, A., Katkovnik, V. Y., & Egiazarian, K. (2006) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.643267 · Cited by 737
Flagged first, then by citations
1 of the 27 references couldn’t be matched to a known paper.
Cited by
Sorted by citations
Items 401–448 of 448
Image Super-Resolution based NCSs Model with Packet Loss
Jiang, C., Li, H., & Zhou, S. (2019) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1229/1/012001
Local and Adaptive Image-to-Image Learning and Inference
Shelhamer, E. (2019) · UC Berkeley
Multi-region processing method for single image deraining
Chen, H., Zhang, Y., Ding, Q., Qiang, H., & Fan, Y. (2019) · Advanced Optical Imaging Technologies · doi:10.1117/12.2537563
An Optimized Image Fusion Method for Fume Removal in Automated Welding Robots Field
Vaz, E. S., Weis, Á. A., Drews, P., Botelho, S. S. D. C., Steffens, C. R., & Pereira, L. (2019) · Latin American Robotics Symposium, Brazilian Symposium on Robotics and Workshop on Robotics in Education (LARS/SBR/WRE) · doi:10.1109/lars-sbr-wre48964.2019.00055
Rain-removing Algorithm for Image Based on Deep Learning
Zou, Q., Wang, J., & Luo, S. (2020) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1533/3/032050
Rain Removal Method Based on Densely Connected Deep Residual Network
Wang, X., Cheng, J., & Huang, W. (2020) · Chinese Control Conference (CCC) · doi:10.23919/ccc50068.2020.9188394
Image deraining using multi-scale aggregated generator network
Zhang, Y., Zhang, J., Wang, F., Guo, M., Cai, L., & Liu, Q. (2020) · Journal of Electronic Imaging · doi:10.1117/1.jei.29.6.063003
Single Image Super-Resolution with Gradient Guidance
Wang, M., & Du, X. (2021) · International Conference on Computer, Control and Robotics (ICCCR) · doi:10.1109/icccr49711.2021.9349371
Raindrop Removal On A Single Image Using The Generative Adversarial Network
MUTTAQIN, M. R., Putra, O. V., & Effendi, L. (2021) · Procedia of Engineering and Life Science · doi:10.21070/pels.v2i0.1163
Robust Attention Deraining Network for Synchronous Rain Streaks and Raindrops RemovalPreprint
Wei, Y., Zhang, Z., Xu, M., Hong, R., Fan, J., & Yan, S. (2021) · doi:10.36227/techrxiv.17205848
Multi-Scale Adaptive Feature Fusion Network for Raindrop Removal
Chen, F., Wu, C., & Niu, Y. (2021) · 2021 4th International Conference on Artificial Intelligence and Pattern Recognition · doi:10.1145/3488933.3488957
Feature enhancement composition model for heavy rain removal on single image
Xu, X., Wang, Q., Pan, X., Pan, Q., Yang, Y., & Wang, C. (2022) · International Conference on Computer Graphics, Artificial Intelligence, and Data Processing (ICCAID) · doi:10.1117/12.2631157
Deep Learning Schätzung absorbierter Strahlungsdosis für die nuklearmedizinische DiagnostikPreprint
Melodia, L. (2020) · Thesis Commons (OSF Preprints) · doi:10.31237/osf.io/pwvc7
BAL-Net: Bi-Attention Learning for Single Image De-raining
Li, Y., Wang, J., Zhenwen, S., Pan, Z., & Wu, B. (2021) · China Automation Congress (CAC) · doi:10.1109/cac53003.2021.9728008
(2016) · Elsevier eBooks · doi:10.1016/b978-0-12-809703-8.09994-9
Robust Attention Deraining Network for Synchronous Rain Streaks and Raindrops RemovalPreprint
Wei, Y., Zhang, Z., Xu, M., Hong, R., Fan, J., & Yan, S. (2022) · doi:10.36227/techrxiv.17205848.v2
Application of Image Defogging Algorithm Based on Deep Learning
Dai, C. (2022) · Lecture notes in electrical engineering · doi:10.1007/978-981-16-8052-6_102
Single Image Raindrop Removal Using a Non-Local Operator and Feature Maps in the Frequency Domain
Ezumi, S., & Ikehara, M. (2022) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.23919/apsipaasc55919.2022.9980200
A Novel Generative Adversarial Network for Joint Deraining and Defogging in Ocean Scene
Zhang, Q., Yu, T., Zhang, H., Chen, J., Zhang, D., Li, L., & Yi, S. (2022) · International Conference on Service Robotics (ICoSR) · doi:10.1109/icosr57188.2022.00020
Deraining of Image Using UNet-Based Conditional Generative Adversarial Network
Bose, S., Chavan, D. R., & Kolekar, M. H. (2023) · Lecture notes in networks and systems · doi:10.1007/978-981-99-1479-1_46
Research on Image Defogging Method Based on Multi-Scale Convolutional Neural Network
汤, 逸. (2023) · Modeling and Simulation · doi:10.12677/mos.2023.125434
Condition Monitoring on Railway Construction Site Using Timelapse Videos
Nicodème, C. (2023) · International Conference on Control, Automation and Systems (ICCAS) · doi:10.23919/iccas59377.2023.10316899
Elemental Attention Mechanism-Guided Progressive Rain Removal Algorithm
Chen, X., Ma, R., Zhang, S., & Zhou, X. (2024) · Lecture notes in computer science · doi:10.1007/978-981-99-9893-7_19
An investigation of rain streak removal models based on expert experience and deep learning
Du, W. (2023) · Highlights in Science Engineering and Technology · doi:10.54097/hset.v56i.9812
A Single Image Rain Removal Algorithm Based on Deep Learning
Zhang, W., Pan, L., Tong, Q., Hai-dong, S., Mi, Y., & Su, S. (2023) · International Conference on Electrical, Mechanical and Computer Engineering (ICEMCE) · doi:10.1109/icemce60359.2023.10490626
EIDA: An Effective Image Deraining Approach Based on Upscaling Method
Jain, A., Kaliyar, R. K., & Sharma, S. (2024) · IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI) · doi:10.1109/iatmsi60426.2024.10502412
Frequency-oriented hierarchical fusion network for single image raindrop removal
Wang, J.-F., Zhang, J., Guo, S., & Li, B. (2024) · PLoS ONE · doi:10.1371/journal.pone.0301439
Single image deraindrop leveraging luminance priors and context aggregation
Liu, Y., Gao, Z. Y., Mei, T., & Han, Y. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.127971
An Image Raindrop Removal Method Based on Squeeze-Excitation and Residual Fusion
Shi, Y., & Gu, L. (2024) · IEEE International Conference on Control, Electronics and Computer Technology (ICCECT) · doi:10.1109/iccect60629.2024.10545865
Ran, L., Hu, Z., Lu, X., & Wu, Z. (2024) · SAE technical papers on CD-ROM/SAE technical paper series · doi:10.4271/2024-01-7032
SGRR: A two-stage method for removing raindrops from ground-based sky maps
Zhang, Y., Zhang, Y., Wang, Y., Ye, X., Xiong, X., Dong, S., & Chen, J. (2024) · Journal of Renewable and Sustainable Energy · doi:10.1063/5.0244467
Influence of Water Droplet Contamination for Transparency Segmentation
Knauthe, V., Weitz, P., Pöllabauer, T., Wirth, T., Rak, A., Kuijper, A., & Fellner, D. W. (2025) · Lecture notes in computer science · doi:10.1007/978-981-97-8705-0_17
Le, V., Go, G.-H., & Pangavhane, S. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5149438
Rain-Free Vision: Leveraging ICA for Enhanced Object Detection with YOLOv8 in Rainy Conditions
Farook, O., & Habib, M. A. (2024) · International Conference on Electrical and Computer Engineering (ICECE) · doi:10.1109/icece64886.2024.11024774
Development of Deep Learning Model for Liver Tumor Detection
Patle, S. K., Verma, P., Thatere, A. B., & Shahu, R. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-2329-7_36
Enhanced UNet-SkipNet Framework for Image Deraining Utilizing Frequency Domain Analysis
Long, J., & Li, S. (2024) · International Conference on Mechatronics and Computer Technology Engineering (MCTE) · doi:10.1109/mcte62870.2024.11117247
Depth Estimation Through Translucent Surfaces
Dai, S., Lou, X. C., Nilsson, P., Thakar, S., Meeker, C., Gordon, A., Kong, X., Zhang, J., Knörlein, B. J., Liu, R., et al. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11127965
Unsupervised Image Restoration Using Domain Discriminator with Feature Disentangle
Zhang, C., Ran, X., & Feng, Z. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-3393-0_1
Image De-Raining Method Based on PReNet and Diffusion Model
Ran, M., Wang, Y., Guan, J., Wu, B., Li, C., & Liu, P. (2025) · International Conference on Image and Video Processing (ICIVP) · doi:10.1109/icivp66296.2025.00021
Robust Few-Shot Semantic Segmentation for Blurred and Occluded Objects in Construction Environments
Salimi, M., Loni, M., Cicchetti, A., & Sirjani, M. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11227444
Research on Rotation-Equivariant Convolution Based Algorithm for Deraining
Tao, S., Lian, J., Cheng, B., & Zhang, Y. (2025) · International Conference on Electronic Information Engineering and Computer Science (EIECS) · doi:10.1109/eiecs67708.2025.11283493
Unsupervised Restoration Method Based on Improved CycleGAN for Multiple Degenerate Images
Wu, L., Feng, Z., Guo, Z., & Zhang, C. (2024) · International Conference on Applied Machine Learning (ICAML) · doi:10.1109/icaml64299.2024.00025
Progressive Dual Branches Guidance Network for Single Image Deraining
Qi, M., Liu, W., Nie, H., & Huang, Z. (2025) · International Conference on Robot Systems and Applications (ICRSA) · doi:10.1109/icrsa66467.2025.11383789
Image prediction algorithm for foggy road scenes based on improved transformer
Zhang, B.-T., Zhao, A.-Y., & Xiong, P. (2026) · Scientific Reports · doi:10.1038/s41598-025-25974-6
Unified Removal of Raindrops and Reflections: A New Benchmark and A Novel Pipeline
Liu, X., He, Z., Chen, Y. F., Zhu, C., Chen, Z., Luo, X., & Lu, Z.-M. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37026-6_36
Prompting Rain Off: Evolving Compact Dual Prompts for Continual De-Raining
Liu, M., Yang, W., & Liu, J. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3689428
Bidirectional multi-scale masked transformer for single image deraining
Qi, M., Liu, W., Huang, Z., & Nie, H. (2026) · Multimedia Systems · doi:10.1007/s00530-026-02392-w
Hybrid swin transformer framework for accurate and efficient single image deraining
Rajeswari, M., & Kodali, P. (2026) · Signal Image and Video Processing · doi:10.1007/s11760-026-05492-2
Metadata
- Authors
- Eigen, D., Krishnan, D., & Fergus, R.
- Affiliations
- New York University (US)
- Venue
- 2013 IEEE International Conference on Computer Vision
- Publisher
- IEEE
- Published
- 2013-12
- Pages
- 633-640
- OpenAlex
- W2154815154
- Semantic Scholar
- 2814db29a34e4ddc83f63c1c0d7b2ae467d337c6
- Cited by
- 454
- References
- 27
- Citations by year
- 2026: 6 · 2025: 24 · 2024: 27 · 2023: 34 · 2022: 44 · 2021: 63 · 2020: 62 · 2019: 48 · 2018: 48 · 2017: 42 · 2016: 35 · 2015: 17 · 2014: 4
- FWCI
- 11.91
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE/CVF International Conference on Computer Vision (ICCV) (publishedVersion)
- Funders
- National Science Foundation
- Microsoft Research
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Enhancement Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image Processing Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image and Signal Denoising Methods
- Keywords
- rain removal, dirt removal, image restoration, single image restoration, convolutional neural networks, outdoor images, water droplets
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
