# Robust 3D Object Detection in Cold Weather Conditions

arXiv: https://arxiv.org/abs/2205.11925 · HTML: https://mlsanity.com/paper/2205.11925/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 31 references that are in the map.
- First posted on arXiv 24 May 2022.

## Builds on (most cited first, 20 of 20)

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection](https://mlsanity.com/paper/1711.06396/) (2017)
- [PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud](https://mlsanity.com/paper/1812.04244/) (2018)
- [AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles](https://mlsanity.com/paper/1705.05065/) (2017)
- [SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloud](https://mlsanity.com/paper/1710.07368/) (2017)
- [SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud](https://mlsanity.com/paper/1809.08495/) (2018)
- [IoU Loss for 2D/3D Object Detection](https://mlsanity.com/paper/1908.03851/) (2019)
- [Complete & Label: A Domain Adaptation Approach to Semantic Segmentation of LiDAR Point Clouds](https://mlsanity.com/paper/2007.08488/) (2020)
- [TANet: Robust 3D Object Detection from Point Clouds with Triple Attention](https://mlsanity.com/paper/1912.05163/) (2019)
- [Fog Simulation on Real LiDAR Point Clouds for 3D Object Detection in Adverse Weather](https://mlsanity.com/paper/2108.05249/) (2021)
- [InstaBoost: Boosting Instance Segmentation via Probability Map Guided Copy-Pasting](https://mlsanity.com/paper/1908.07801/) (2019)
- [Physics-Based Rendering for Improving Robustness to Rain](https://mlsanity.com/paper/1908.10335/) (2019)
- [Lidar Light Scattering Augmentation (LISA): Physics-based Simulation of Adverse Weather Conditions for 3D Object Detection](https://mlsanity.com/paper/2107.07004/) (2021)
- [CNN-based Lidar Point Cloud De-Noising in Adverse Weather](https://mlsanity.com/paper/1912.03874/) (2019)
- [A Benchmark for Lidar Sensors in Fog: Is Detection Breaking Down?](https://mlsanity.com/paper/1912.03251/) (2019)
- [RoarNet: A Robust 3D Object Detection based on RegiOn Approximation Refinement](https://mlsanity.com/paper/1811.03818/) (2018)
- [Robustness of Object Detectors in Degrading Weather Conditions](https://mlsanity.com/paper/2106.08795/) (2021)
- [A Benchmark for Spray from Nearby Cutting Vehicles](https://mlsanity.com/paper/2108.10800/) (2021)

## Built on by (most cited first, 7 of 7)

- [Sunshine to Rainstorm: Cross-Weather Knowledge Distillation for Robust 3D Object Detection](https://mlsanity.com/paper/2402.18493/) (2024)
- [Energy-based Detection of Adverse Weather Effects in LiDAR Data](https://mlsanity.com/paper/2305.16129/) (2023)
- [LS-VOS: Identifying Outliers in 3D Object Detections Using Latent Space Virtual Outlier Synthesis](https://mlsanity.com/paper/2310.00952/) (2023)
- [Towards Robust 3D Object Detection In Rainy Conditions](https://mlsanity.com/paper/2310.00944/) (2023)
- [SemanticSpray++: A Multimodal Dataset for Autonomous Driving in Wet Surface Conditions](https://mlsanity.com/paper/2406.09945/) (2024)
- [Label-Efficient Semantic Segmentation of LiDAR Point Clouds in Adverse Weather Conditions](https://mlsanity.com/paper/2406.09906/) (2024)
- [WILD SAM: A Simulated-and-Real Data Augmentation for Autonomous Driving Perception under Challenging Weather](https://mlsanity.com/paper/2605.01081/) (2026)

## Abstract (arXiv)

Adverse weather conditions can negatively affect LiDAR-based object detectors. In this work, we focus on the phenomenon of vehicle gas exhaust condensation in cold weather conditions. This everyday effect can influence the estimation of object sizes, orientations and introduce ghost object detections, compromising the reliability of the state of the art object detectors. We propose to solve this problem by using data augmentation and a novel training loss term. To effectively train deep neural networks, a large set of labeled data is needed. In case of adverse weather conditions, this process can be extremely laborious and expensive. We address this issue in two steps: First, we present a gas exhaust data generation method based on 3D surface reconstruction and sampling which allows us to generate large sets of gas exhaust clouds from a small pool of labeled data. Second, we introduce a point cloud augmentation process that can be used to add gas exhaust to datasets recorded in good weather conditions. Finally, we formulate a new training loss term that leverages the augmented point cloud to increase object detection robustness by penalizing predictions that include noise. In contrast to other works, our method can be used with both grid-based and point-based detectors. Moreover, since our approach does not require any network architecture changes, inference times remain unchanged. Experimental results on real data show that our proposed method greatly increases robustness to gas exhaust and noisy data.