# TripleMixer: A 3D Point Cloud Denoising Model for Adverse Weather

arXiv: https://arxiv.org/abs/2408.13802 · HTML: https://mlsanity.com/paper/2408.13802/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 75 references that are in the map.
- First posted on arXiv 25 Aug 2024.

## Builds on (most cited first, 30 of 39)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Point Transformer V3: Simpler, Faster, Stronger](https://mlsanity.com/paper/2312.10035/) (2023)
- [Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation](https://mlsanity.com/paper/2011.10033/) (2020)
- [PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation](https://mlsanity.com/paper/2003.14032/) (2020)
- [SalsaNext: Fast, Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Driving](https://mlsanity.com/paper/2003.03653/) (2020)
- [The Oxford Radar RobotCar Dataset: A Radar Extension to the Oxford RobotCar Dataset](https://mlsanity.com/paper/1909.01300/) (2019)
- [Robo3D: Towards Robust and Reliable 3D Perception against Corruptions](https://mlsanity.com/paper/2303.17597/) (2023)
- [Spherical Transformer for LiDAR-based 3D Recognition](https://mlsanity.com/paper/2303.12766/) (2023)
- [Benchmarking Robustness of 3D Object Detection to Common Corruptions in Autonomous Driving](https://mlsanity.com/paper/2303.11040/) (2023)
- [Learning Guided Convolutional Network for Depth Completion](https://mlsanity.com/paper/1908.01238/) (2019)
- [Fog Simulation on Real LiDAR Point Clouds for 3D Object Detection in Adverse Weather](https://mlsanity.com/paper/2108.05249/) (2021)
- [Canadian Adverse Driving Conditions Dataset](https://mlsanity.com/paper/2001.10117/) (2020)
- [Perception and Sensing for Autonomous Vehicles Under Adverse Weather Conditions: A Survey](https://mlsanity.com/paper/2112.08936/) (2021)
- [Boreas: A Multi-Season Autonomous Driving Dataset](https://mlsanity.com/paper/2203.10168/) (2022)
- [LiDAR Snowfall Simulation for Robust 3D Object Detection](https://mlsanity.com/paper/2203.15118/) (2022)
- [OverlapTransformer: An Efficient and Rotation-Invariant Transformer Network for LiDAR-Based Place Recognition](https://mlsanity.com/paper/2203.03397/) (2022)
- [3D Object Detection from Images for Autonomous Driving: A Survey](https://mlsanity.com/paper/2202.02980/) (2022)
- [Transformation-Equivariant 3D Object Detection for Autonomous Driving](https://mlsanity.com/paper/2211.11962/) (2022)
- [3D Semantic Segmentation in the Wild: Learning Generalized Models for Adverse-Condition Point Clouds](https://mlsanity.com/paper/2304.00690/) (2023)
- [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)
- [DSOR: A Scalable Statistical Filter for Removing Falling Snow from LiDAR Point Clouds in Severe Winter Weather](https://mlsanity.com/paper/2109.07078/) (2021)
- [LIBRE: The Multiple 3D LiDAR Dataset](https://mlsanity.com/paper/2003.06129/) (2020)
- [Weather Influence and Classification with Automotive Lidar Sensors](https://mlsanity.com/paper/1906.07675/) (2019)
- [Survey on LiDAR Perception in Adverse Weather Conditions](https://mlsanity.com/paper/2304.06312/) (2023)
- [UniMix: Towards Domain Adaptive and Generalizable LiDAR Semantic Segmentation in Adverse Weather](https://mlsanity.com/paper/2404.05145/) (2024)
- [CVTNet: A Cross-View Transformer Network for Place Recognition Using LiDAR Data](https://mlsanity.com/paper/2302.01665/) (2023)
- [MultiCorrupt: A Multi-Modal Robustness Dataset and Benchmark of LiDAR-Camera Fusion for 3D Object Detection](https://mlsanity.com/paper/2402.11677/) (2024)
- [LSK3DNet: Towards Effective and Efficient 3D Perception with Large Sparse Kernels](https://mlsanity.com/paper/2403.15173/) (2024)

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

- [ResLPR: A LiDAR Data Restoration Network and Benchmark for Robust Place Recognition Against Weather Corruptions](https://mlsanity.com/paper/2503.12350/) (2025)
- [OmniLiDAR: A Unified Diffusion Framework for Multi-Domain 3D LiDAR Generation](https://mlsanity.com/paper/2605.13815/) (2026)
- [Deep Learning For Point Cloud Denoising: A Survey](https://mlsanity.com/paper/2508.11932/) (2025)
- [REHEARSE-3D: A Multi-modal Emulated Rain Dataset for 3D Point Cloud De-raining](https://mlsanity.com/paper/2504.21699/) (2025)
- [DenoiseCP-Net: Efficient Collective Perception in Adverse Weather via Joint LiDAR-Based 3D Object Detection and Denoising](https://mlsanity.com/paper/2507.06976/) (2025)
- [Source-Only Cross-Weather LiDAR via Geometry-Aware Point Drop](https://mlsanity.com/paper/2511.01250/) (2025)
- [LIORNet: Self-Supervised LiDAR Snow Removal Framework for Autonomous Driving under Adverse Weather Conditions](https://mlsanity.com/paper/2603.19936/) (2026)

## Abstract (arXiv)

Adverse weather conditions such as snow, fog, and rain pose significant challenges to LiDAR-based perception models by introducing noise and corrupting point cloud measurements. To address this issue, we propose TripleMixer, a robust and efficient point cloud denoising network that integrates spatial, frequency, and channel-wise processing through three specialized mixer modules. TripleMixer effectively suppresses high-frequency noise while preserving essential geometric structures and can be seamlessly deployed as a plug-and-play module within existing LiDAR perception pipelines. To support the development and evaluation of denoising methods, we construct two large-scale simulated datasets, Weather-KITTI and Weather-NuScenes, covering diverse weather scenarios with dense point-wise semantic and noise annotations. Based on these datasets, we establish four benchmarks: Denoising, Semantic Segmentation (SS), Place Recognition (PR), and Object Detection (OD). These benchmarks enable systematic evaluation of denoising generalization, transferability, and downstream impact under both simulated and real-world adverse weather conditions. Extensive experiments demonstrate that TripleMixer achieves state-of-the-art denoising performance and yields substantial improvements across all downstream tasks without requiring retraining. Our results highlight the potential of denoising as a task-agnostic preprocessing strategy to enhance LiDAR robustness in real-world autonomous driving applications.