Seeing Through Fog Without Seeing Fog: Deep Multimodal Sensor Fusion in Unseen Adverse Weather
Open accessThe DOI matches its Crossref record; 88 of the 88 references it cites were found in a registry or an index.
Abstract
The fusion of multimodal sensor streams, such as camera, lidar, and radar measurements, plays a critical role in object detection for autonomous vehicles, which base their decision making on these inputs. While existing methods exploit redundant information in good environmental conditions, they fail in adverse weather where the sensory streams can be asymmetrically distorted. These rare ``edge-case'' scenarios are not represented in available datasets, and existing fusion architectures are not designed to handle them. To address this challenge we present a novel multimodal dataset acquired in over 10,000~km of driving in northern Europe. Although this dataset is the first large multimodal dataset in adverse weather, with 100k labels for lidar, camera, radar, and gated NIR sensors, it does not facilitate training as extreme weather is rare. To this end, we present a deep fusion network for robust fusion without a large corpus of labeled training data covering all asymmetric distortions. Departing from proposal-level fusion, we propose a single-shot model that adaptively fuses features, driven by measurement entropy. We validate the proposed method, trained on clean data, on our extensive validation dataset. Code and data are available here https://github.com/princeton-computational-imaging/SeeingThroughFog.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472
Scikit-learn: Machine Learning in Python
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Müller, A., Nothman, J., Louppe, G., et al. (2012) · arXiv · doi:10.48550/arxiv.1201.0490 · Cited by 71,016
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1506.01497 · Cited by 70,812
Image quality assessment: from error visibility to structural similarity
Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P. (2004) · IEEE Transactions on Image Processing · doi:10.1109/tip.2003.819861 · Cited by 57,892
(2016) · Cited by 31,590
Feature Pyramid Networks for Object Detection
Lin, T.-Y., Dollar, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.106 · Cited by 30,939
Girshick, R. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.169 · Cited by 28,105
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
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 · cited 1×
“These priors are either hand-crafted [25] and used for depth and transmission estimation separately, or they are learned jointly as part of trainable end-to-end models [38, 32, 73].”
Background
Research works printed but not linked: 3
- inbar, 2008, Laser gated camera imaging system and method
- 10.1515/aot-2014-0001 · doi:10.1515/aot-2014-0001
- 2005, Fog definition, Federal Meteorological Handbook No 1 Surface Weather Observations and Reports U S Department of Commerce / National Oceanic and Atmospheric Administration
Cited by
Feng, D., Haase-Schutz, C., Rosenbaum, L., Hertlein, H., Glaser, C., Timm, F., Wiesbeck, W., & Dietmayer, K. (2021) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2020.2972974 · Cited by 1,425
Self-citationACDC: The Adverse Conditions Dataset with Correspondences for Semantic Driving Scene Understanding
Sakaridis, C., Dai, D., & Van Gool, L. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01059 · Cited by 572
Deep Learning Sensor Fusion for Autonomous Vehicle Perception and Localization: A Review
Fayyad, J., Jaradat, M. A., Gruyer, D., & Najjaran, H. (2020) · Sensors · doi:10.3390/s20154220 · Cited by 498
Yao, S., Guan, R., Huang, X., Li, Z., Sha, X., Yue, Y., Lim, E. G., Seo, H., Man, K. L., Zhu, X., et al. (2024) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2023.3307157 · Cited by 265
Robust Multimodal Vehicle Detection in Foggy Weather Using Complementary Lidar and Radar Signals
Qian, K., Zhu, S., Zhang, X., & Li, L. E. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00051 · Cited by 206
“Aside from lidar and camera, radar has been widely deployed on autonomous vehicles [6, 3, 58] and has the potential to overcome foggy weather.”
BackgroundMethodInfluentialDomain Adaptive Object Detection for Autonomous Driving under Foggy Weather
Li, J., Xu, R., Ma, J., Zou, Q., Ma, J., & Yu, H. (2023) · 2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv56688.2023.00068 · Cited by 160
“[2] develop a network that takes the data from four sensors as input: lidar, RGB camera, gated camera, and radar.”
BackgroundMethodA Comprehensive Survey on Deep Learning Multi-Modal Fusion: Methods, Technologies and Applications
Jiao, T., Guo, C., Feng, X., Chen, Y., & Song, J. (2024) · Computers, Materials & Continua · doi:10.32604/cmc.2024.053204 · Cited by 158
RCBEVDet: Radar-Camera Fusion in Bird's Eye View for 3D Object Detection
Lin, Z., Liu, Z., Xia, Z., Wang, X., Wang, Y., Qi, S., Dong, Y., Dong, N., Zhang, L., & Zhu, C. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.01414 · Cited by 153
3D Object Detection from Images for Autonomous Driving: A Survey
Ma, X., Ouyang, W., Simonelli, A., & Ricci, E. (2022) · arXiv · doi:10.48550/arxiv.2202.02980 · Cited by 147
Tahir, N. U. A., Zhang, Z., Asim, M., Chen, J., & ELAffendi, M. (2024) · Algorithms · doi:10.3390/a17030103 · Cited by 145
Are We Hungry for 3D LiDAR Data for Semantic Segmentation? A Survey of Datasets and Methods
Gao, B., Pan, Y., Li, C., Geng, S., & Zhao, H. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2021.3076844 · Cited by 105
Emerging trends in autonomous vehicle perception: Multimodal fusion for 3D object detection
Alaba, S. Y., Gurbuz, A. C., & Ball, J. E. (2024) · World Electric Vehicle Journal · doi:10.3390/wevj15010020 · Cited by 82
“Moreover, there are additional Radar datasets for autonomous driving, such as SeeingThroughFog [49], AIODrive [50], VoD [51], TJ4DRadSet [52], K-Radar [53] and aiMotive [54].”
MethodMeasuring the Influence of Environmental Conditions on Automotive Lidar Sensors
Linnhoff, C., Hofrichter, K., Elster, L., Rosenberger, P., & Winner, H. (2022) · Sensors · doi:10.3390/s22145266 · Cited by 44
“In this category, dynamic data sets exist recorded with test vehicles on the road in different weather conditions, such as nuScenes [17], SeeingThroughFog [18], and RADIATE [19].”
BackgroundA Survey on Multi-Sensor Fusion Perimeter Intrusion Detection in High-Speed Railways
Shi, T., Guo, P., Wang, R., Ma, Z., Zhang, W., Li, W., Fu, H., & Hu, H. (2024) · Sensors · doi:10.3390/s24175463 · Cited by 42
“Mario has proposed a method for multimodal recognition under adverse weather conditions, combining lidar, radar, cameras, and infrared thermal imaging, introducing a deep fusion network for robust fusion that incorporates an entropy-based approach and adaptive fusion features [99].”
MethodOccFusion: Multi-Sensor Fusion Framework for 3D Semantic Occupancy Prediction
Ming, Z., Stephany Berrio, J., Shan, M., & Worrall, S. (2025) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2024.3453293 · Cited by 35
“Due to the complementary property of multi-sensor fusion, people in this domain also investigate the camera-lidar-radar fusion strategy and its performance in environment perception.”
I Had a Bad Day: Challenges of Object Detection in Bad Visibility Conditions
Rothmeier, T., Wachtel, D., von Dem Bussche-Hünnefeld, T., & Huber, W. (2023) · 2023 IEEE Intelligent Vehicles Symposium (IV) · doi:10.1109/iv55152.2023.10186674 · Cited by 21
“4 million frames were collected in the dense project [6], yet only a minor amount include adverse weather (2.”
Background
Metadata
- Authors
- Bijelic, M., Gruber, T., Mannan, F., Kraus, F., Ritter, W., Dietmayer, K., & Heide, F.
- Venue
- 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2020-06
- Pages
- 11679-11689
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W3005354951
- Cited by
- 609
- References
- 88
- FWCI
- 48.24
- Type
- conference paper
- Language
- en
- Open access
- green
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.