RECORD
Towards Robust 3D Object Detection In Rainy Conditions
Computer Vision and Pattern Recognition · Submitted 2 Oct 2023
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim Tests on real-world data show that our approach improves the robustness to road spray of several popular 3D object detectors.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
LiDAR sensors are used in autonomous driving applications to accurately perceive the environment. However, they are affected by adverse weather conditions such as snow, fog, and rain. These everyday phenomena introduce unwanted noise into the measurements, severely degrading the performance of LiDAR-based perception systems. In this work, we propose a framework for improving the robustness of LiDAR-based 3D object detectors against road spray. Our approach uses a state-of-the-art adverse weather detection network to filter out spray from the LiDAR point cloud, which is then used as input for the object detector. In this way, the detected objects are less affected by the adverse weather in the scene, resulting in a more accurate perception of the environment. In addition to adverse weather filtering, we explore the use of radar targets to further filter false positive detections. Tests on real-world data show that our approach improves the robustness to road spray of several popular 3D object detectors.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | LiDAR sensors are used in autonomous driving applications to accurately perceive the environment. | background 1.00 | 0.04 | 0.01 | asserted 1.00 |
| s1 | However, they are affected by adverse weather conditions such as snow, fog, and rain. | background 1.00 | 0.05 | 0.02 | asserted 1.00 |
| s2 | These everyday phenomena introduce unwanted noise into the measurements, severely degrading the performance of LiDAR-based perception systems. | background 1.00 | 0.06 | 0.02 | asserted 1.00 |
| s3 | In this work, we propose a framework for improving the robustness of LiDAR-based 3D object detectors against road spray. | contribution 1.00 | 0.85 | 0.11 | asserted 0.93 |
| s4 | Our approach uses a state-of-the-art adverse weather detection network to filter out spray from the LiDAR point cloud, which is then used as input for the object detector. | method 0.98 | 0.83 | 0.06 | asserted 1.00 |
| s5 | In this way, the detected objects are less affected by the adverse weather in the scene, resulting in a more accurate perception of the environment. | interpretation 0.79 | 0.40 | 0.32 | asserted 0.98 |
| s6 | In addition to adverse weather filtering, we explore the use of radar targets to further filter false positive detections. | method 0.67 | 0.84 | 0.04 | asserted 0.57 |
| s7 | Tests on real-world data show that our approach improves the robustness to road spray of several popular 3D object detectors. | result 1.00 | 0.96 | 0.74 | asserted 1.00 |
What was examined, and what was not
- arXiv listing abstract v2
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
LiDAR sensors are used in autonomous driving applications to accurately perceive the environment. However, they are affected by adverse weather conditions such as snow, fog, and rain. These everyday phenomena introduce unwanted noise into the measurements, severely degrading the performance of LiDAR-based perception systems. In this work, we propose a framework for improving the robustness of LiDAR-based 3D object detectors against road spray. Our approach uses a state-of-the-art adverse weather detection network to filter out spray from the LiDAR point cloud, which is then used as input for the object detector. In this way, the detected objects are less affected by the adverse weather in the scene, resulting in a more accurate perception of the environment. In addition to adverse weather filtering, we explore the use of radar targets to further filter false positive detections. Tests on real-world data show that our approach improves the robustness to road spray of several popular 3D object detectors.
Human review
How the literature uses it
What this paper does with the arXiv papers it cites
What it cites · 5 sentences without a confident label
Uses the method or tool of 2 papers
-
Similar to [ref] , we generate object detections using a high-performing 3D object detector (in our case VoxelNeXt [ref] ).
Simulating Road Spray Effects in Automotive Lidar Sensor Models · Experiment Setup · 0.98
-
We use AWNet [ref] as the primary method for spray detection and additionally provide the results when using other adverse weather detection methods, namely Particle-VoxelNet [ref] , Particle-UNet [ref] , WeatherNet [ref] , and DSOR [ref] .
DSOR: A Scalable Statistical Filter for Removing Falling Snow from LiDAR Point Clouds in Severe Winter Weather · Experiment Setup · 0.87
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.