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
Fully convolutional networks for semantic segmentation
Long, J., Shelhamer, E., & Darrell, T. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298965 · Cited by 38,834
Fully convolutional networks for semantic segmentation
Shelhamer, E., Long, J., & Darrell, T. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2572683 · Cited by 11,898
Image Super-Resolution Using Deep Convolutional Networks
Dong, C., Loy, C. C., He, K., & Tang, X. (2016) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2015.2439281 · Cited by 10,105
Learning a Deep Convolutional Network for Image Super-Resolution
Dong, C., Loy, C. C., He, K., & Tang, X. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-10593-2_13 · Cited by 5,910
DehazeNet: An End-to-End System for Single Image Haze Removal
Cai, B., Xu, X., Jia, K., Qing, C., & Tao, D. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2016.2598681 · Cited by 3,367
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
