SoilingNet: Soiling Detection on Automotive Surround-View Cameras
Open accessAbstract
Cameras are an essential part of sensor suite in autonomous driving. Surround-view cameras are directly exposed to external environment and are vulnerable to get soiled. Cameras have a much higher degradation in performance due to soiling compared to other sensors. Thus it is critical to accurately detect soiling on the cameras, particularly for higher levels of autonomous driving. We created a new dataset having multiple types of soiling namely opaque and transparent. It will be released publicly as part of our WoodScape dataset [15] to encourage further research. We demonstrate high accuracy using a Convolutional Neural Network (CNN) based architecture. We also show that it can be combined with the existing object detection task in a multi-task learning framework. Finally, we make use of Generative Adversarial Networks (GANs) to generate more images for data augmentation and show that it works successfully similar to the style transfer.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
Existing studies mainly focused on classification or patch-based detection, providing limited spatial understanding of contamination.
“However, these studies mainly focused on classification or patch-based detection, providing limited spatial understanding of contamination.”
From AI-Based Image Quality and Lens Defect Analysis in Autonomous Driving: A Framework with U-Net-Based Soiling Detection (2025) · cites this paper as [1]
The Formal definition (pp. 2–3) describes image-level classification and tile-level detection, supporting that characterization of SoilingNet. But it explicitly says tile-level detection provides higher spatial resolution, and Proposed CNN architecture (p. 4) reports an output configuration at image resolution. The claim’s suggestion that this study provides only limited spatial understanding therefore overstates what the source shows. (LLM, conf=0.85)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Unpaired image-to-image translation using cycle-consistent adversarial networks
Zhu, J.-Y., Park, T., Isola, P., & Efros, A. A. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.244 · Cited by 23,602 · 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
Multimodal Unsupervised Image-to-Image Translation
Huang, X., Liu, M.-Y., Belongie, S., & Kautz, J. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01219-9_11 · Cited by 2,597 · see citing works
Fattal, R. (2008) · ACM Transactions on Graphics · doi:10.1145/1360612.1360671 · Cited by 2,141 · see citing works
Berman, D., Treibitz, T., & Avidan, S. (2016) · 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.2016.185 · Cited by 1,685 · see citing works
Semantic Foggy Scene Understanding with Synthetic Data
Sakaridis, C., Dai, D., & Gool, L. V. (2018) · International Journal of Computer Vision · doi:10.1007/s11263-018-1072-8 · Cited by 1,354 · see citing works
WoodScape: A Multi-Task, Multi-Camera Fisheye Dataset for Autonomous Driving
Yogamani, S., Hughes, C., Horgan, J., Sistu, G., Chennupati, S., Uricar, M., Milz, S., Simon, M., Amende, K., Witt, C., et al. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00940 · Cited by 303 · cited 2× · see citing works
“duced in our WoodScape dataset paper [15].”
BackgroundSelf-citationComputer vision in automated parking systems: Design, implementation and challenges
Heimberger, M., Horgan, J., Hughes, C., McDonald, J., & Yogamani, S. (2017) · Image and Vision Computing · doi:10.1016/j.imavis.2017.07.002 · Cited by 126 · see citing works
Self-citationI Can See Clearly Now: Image Restoration via De-Raining
Porav, H., Bruls, T., & Newman, P. M. (2019) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2019.8793486 · Cited by 103 · see citing works
Vision-Based Driver Assistance Systems: Survey, Taxonomy and Advances
Horgan, J., Hughes, C., McDonald, J., & Yogamani, S. (2015) · 2015 IEEE 18th International Conference on Intelligent Transportation Systems · doi:10.1109/itsc.2015.329 · Cited by 72 · see citing works
Self-citationYes, we GAN: Applying adversarial techniques for autonomous driving
Uřičář, M., Křížek, P., Hurych, D., Sobh, I., Yogamani, S. K., & Denny, P. E. (2019) · Electronic Imaging · doi:10.2352/issn.2470-1173.2019.15.avm-048 · Cited by 54 · see citing works
Self-citationKi, S., Sim, H., Choi, J.-S., Kim, S. Y., Seo, S., Kim, S., & Kim, M. (2018) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2018.00126 · Cited by 37 · see citing works
Real-time Joint Object Detection and Semantic Segmentation Network for Automated DrivingPreprint
Sistu, G., Leang, I., & Yogamani, S. K. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.03912 · Cited by 36 · see citing works
Self-citationNeurAll: Towards a Unified Visual Perception Model for Automated Driving
Sistu, G., Leang, I., Chennupati, S., Yogamani, S. K., Eising, C., Milz, S., & Rawashdeh, S. A. (2019) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2019.8917043 · Cited by 30 · see citing works
Self-citationNeurAll: Towards a Unified Model for Visual Perception in Automated DrivingPreprint
Sistu, G., Leang, I., Chennupati, S., Hughes, C., Milz, S., Yogamani, S. K., & Rawashdeh, S. A. (2019) · arXiv (Cornell University) · Cited by 11 · see citing works
Self-citationNeurAll: Towards a Unified Visual Perception Model for Automated DrivingPreprint
Sistu, G., Leang, I., Chennupati, S., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.03589
Self-citation
Flagged first, then by citations
Research works printed but not linked: 2
- [4][4] I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio. Generative adversarial nets. In Advances in neural information processing systems , pages 2672-2680, 2014. -
- [17][17] CVPR 2019 UG2 Challenge. http://www.ug2challenge. org/ , 2019 (accessed April 12, 2019). TABLE III: Summary of results of Image-level soiling classification | | Normalized Confusion Matrix | Normalized Confusion Matrix | Normalized Confusion Matrix | Normalized Confusion Matrix | Raw Confusion Matrix | Raw Confusion Matrix | Raw Confusion Matrix | Raw Confusion Matrix | |----------------------------------------------------|----------------------------------------------------|----------------------------------------------------|----------------------------------------------------|----------------------------------------------------|----------------------------------------------------|----------------------------------------------------|----------------------------------------------------|----------------------------------------------------| | Training and Testing on front/rear cameras | Training and Testing on front/rear cameras | Training and Testing on front/rear cameras | Training and Testing on front/rear cameras | Training and Testing on front/rear cameras | Training and Testing on front/rear cameras | Training and Testing on front/rear cameras | Training and Testing on front/rear cameras | Training and Testing on front/rear cameras | | - | Clean | Transparent | Opaque | Both | Clean | Transparent | Opaque | Both | | Clean | 1 | 0 | 0 | 0 | 14600 | 0 | 17 | 0 | | Transparent | 0.06 | 0.92 | 0 | 0.02 | 225 | 3730 | 13 | 91 | | Opaque | 0.02 | 0.02 | 0.94 | 0.03 | 135 | 134 | 7913 | 240 | | Both | 0 | 0 | 0.04 | 0.94 | 0 | 9 | 191 | 4818 | | on front/rear cameras and Testing on all cameras | on front/rear cameras and Testing on all cameras | on front/rear cameras and Testing on all cameras | on front/rear cameras and Testing on all cameras | on front/rear cameras and Testing on all cameras | on front/rear cameras and Testing on all cameras | on front/rear cameras and Testing on all cameras | on front/rear cameras and Testing on all cameras | on front/rear cameras and Testing on all cameras | | - | Clean | Transparent | Opaque | Both | Clean | Transparent | Opaque | Both | | Clean | 0.7 | 0 | 0.28 | 0.02 | 20563 | 1 | 8280 | 510 | | Transparent | 0.14 | 0.52 | 0.29 | 0.06 | 1145 | 4192 | 2337 | 463 | | Opaque | 0.02 | 0.01 | 0.92 | 0.06 | 255 | 209 | 15401 | 952 | | Both | 0.01 | 0 | 0.12 | 0.87 | 73 | 14 | 1206 | 8441 | | Training on all cameras and Testing on all cameras | Training on all cameras and Testing on all cameras | Training on all cameras and Testing on all cameras | Training on all cameras and Testing on all cameras | Training on all cameras and Testing on all cameras | Training on all cameras and Testing on all cameras | Training on all cameras and Testing on all cameras | Training on all cameras and Testing on all cameras | Training on all cameras and Testing on all cameras | | - | Clean | Transparent | Opaque | Both | Clean | Transparent | Opaque | Both | | Clean | 1 | 0 | 0 | 0 | 29333 | 11 | 8 | 2 | | Transparent | 0 | 0.99 | 0 | 0 | 25 | 8073 | 1 | 38 | | Opaque | 0 | 0 | 1 | 0 | 0 | 0 | 16816 | 1 | | Both | 0 | 0 | 0 | 1 | 0 | 13 | 14 | 9707 | Fig. 5: The results obtained from the CycleGAN proof of concept for the problem of soiling and adverse weather classification. The legend per each quadruple of images: the top left image shows the original clean image; the top right image is the generated 'soiled' version of this clean image. The bottom left image is the original soiled image; the bottom right image is the 'clean' version of this soiled image. <!-- image -->
Cited by
Sorted by citations
Deep reinforcement learning for autonomous driving: A survey
Kiran, B. R., Sobh, I., Talpaert, V., Mannion, P., Sallab, A. A. A., Yogamani, S., & Perez, P. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2021.3054625 · Cited by 2,342 · see citing works
Self-citationOmniDet: Surround View Cameras Based Multi-Task Visual Perception Network for Autonomous Driving
Ravi Kumar, V., Yogamani, S., Rashed, H., Sitsu, G., Witt, C., Leang, I., Milz, S., & Mader, P. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3062324 · Cited by 117 · see citing works
“Compared to our previous work SoilingNet [7], we moved from the tiled output to pixel-level segmentation.”
BackgroundMethodSelf-citationLet’s Get Dirty: GAN Based Data Augmentation for Camera Lens Soiling Detection in Autonomous Driving
Uricar, M., Sistu, G., Rashed, H., Vobecky, A., Kumar, V. R., Krizek, P., Burger, F., & Yogamani, S. (2021) · 2021 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv48630.2021.00081 · Cited by 51 · see citing works
Self-citationDas, A., Krizek, P., Sistu, G., Burger, F., Madasamy, S., Uricar, M., Kumar, V. R., & Yogamani, S. (2020) · 2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc45102.2020.9294677 · Cited by 25 · see citing works
Self-citationO’g’li, A. (2025) · American Journal of Mechanics and Applications · doi:10.11648/j.ajma.20251204.14
- Authors
- Uricar, M., Krizek, P., Sistu, G., & Yogamani, S.
- Affiliations
- Valeo (Ireland) (IE)
- Venue
- 2019 IEEE Intelligent Transportation Systems Conference (ITSC)
- Publisher
- IEEE
- Published
- 2019-10
- Pages
- 67-72
- OpenAlex
- W2942874149
- Cited by
- 55
- References
- 16
- Citations by year
- 2026: 3 · 2025: 7 · 2024: 10 · 2023: 8 · 2022: 6 · 2021: 12 · 2020: 5 · 2019: 4
- FWCI
- 2.20
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE International Conference on Intelligent Transportation Systems (ITSC) (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Engineering › Automotive Engineering › Autonomous Vehicle Technology and Safety
- Physical Sciences › Engineering › Industrial and Manufacturing Engineering › Industrial Vision Systems and Defect Detection
- Keywords
- surround-view cameras, autonomous driving, multi-task learning, object detection, generative adversarial networks, data augmentation, style transfer, convolutional neural networks, sensor degradation
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
