Saved in:
Bibliographic Details
Main Authors: Zhao, Xiongwei, Wen, Congcong, Zhu, Xu, Wang, Yang, Bai, Haojie, Dou, Wenhao
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2408.13802
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908497202905088
author Zhao, Xiongwei
Wen, Congcong
Zhu, Xu
Wang, Yang
Bai, Haojie
Dou, Wenhao
author_facet Zhao, Xiongwei
Wen, Congcong
Zhu, Xu
Wang, Yang
Bai, Haojie
Dou, Wenhao
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2408_13802
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle TripleMixer: A 3D Point Cloud Denoising Model for Adverse Weather
Zhao, Xiongwei
Wen, Congcong
Zhu, Xu
Wang, Yang
Bai, Haojie
Dou, Wenhao
Computer Vision and Pattern Recognition
Robotics
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.
title TripleMixer: A 3D Point Cloud Denoising Model for Adverse Weather
topic Computer Vision and Pattern Recognition
Robotics
url https://arxiv.org/abs/2408.13802