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

• URL: http://arxiv.org/abs/2408.13802v2
• Date: Thu, 21 Aug 2025 14:05:53 GMT
• Title: TripleMixer: A 3D Point Cloud Denoising Model for Adverse Weather
• Authors: Xiongwei Zhao, Congcong Wen, Xu Zhu, Yang Wang, Haojie Bai, Wenhao Dou,
• Abstract summary: Adverse weather conditions pose significant challenges to LiDAR-based perception models.<n>We propose TripleMixer, a point cloud denoising network that integrates spatial, frequency, and channel-wise processing.<n>Extensive experiments demonstrate that TripleMixer achieves state-of-the-art denoising performance.
• Score: 10.564182855472328
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Noise-Robust Tiny Object Localization with Flows [63.60972031108944]
  We propose a noise-robust localization framework leveraging normalizing flows for flexible error modeling and uncertainty-guided optimization.<n>Our method captures complex, non-Gaussian prediction distributions through flow-based error modeling, enabling robust learning under noisy supervision.<n>An uncertainty-aware gradient modulation mechanism further suppresses learning from high-uncertainty, noise-prone samples, mitigating overfitting while stabilizing training.
  arXiv  Detail & Related papers  (2026-01-02T09:16:55Z)
• Adaptive Dual-Weighted Gravitational Point Cloud Denoising Method [10.397999108705962]
  This paper proposes an adaptive dual-weight gravitational-based point cloud denoising method.<n>It achieves consistent improvements in F1, PSNR, and Chamfer Distance across various noise conditions.<n>It also reduces the single-frame processing time, thereby validating its high accuracy, robustness, and real-time performance in multi-noise scenarios.
  arXiv  Detail & Related papers  (2025-12-11T07:49:28Z)
• U-CAN: Unsupervised Point Cloud Denoising with Consistency-Aware Noise2Noise Matching [87.76453413654922]
  We introduce U-CAN, an Unsupervised framework for point cloud denoising with Consistency-Aware Noise2Noise matching.<n>Specifically, we leverage a neural network to infer a multi-step denoising path for each point of a shape or scene with a noise to noise matching scheme.<n>We introduce a novel constraint on the denoised geometry consistency for learning consistency-aware denoising patterns.
  arXiv  Detail & Related papers  (2025-10-29T06:20:21Z)
• Mitigating the Noise Shift for Denoising Generative Models via Noise Awareness Guidance [54.88271057438763]
  Noise Awareness Guidance (NAG) is a correction method that explicitly steers sampling trajectories to remain consistent with the pre-defined noise schedule.<n>NAG consistently mitigates noise shift and substantially improves the generation quality of mainstream diffusion models.
  arXiv  Detail & Related papers  (2025-10-14T13:31:34Z)
• InJecteD: Analyzing Trajectories and Drift Dynamics in Denoising Diffusion Probabilistic Models for 2D Point Cloud Generation [48.55037712252843]
  InJecteD is a framework for interpreting Denoising Diffusion Probabilistic Models (DDPMs)<n>We apply this framework to three datasets from the Datasaurus Dozen bullseye, dino, and circle.<n>Our approach quantifies trajectory properties, including displacement, velocity, clustering, and drift field dynamics.
  arXiv  Detail & Related papers  (2025-09-09T14:53:19Z)
• DenoiseCP-Net: Efficient Collective Perception in Adverse Weather via Joint LiDAR-Based 3D Object Detection and Denoising [0.5714074111744111]
  We conduct the first study of LiDAR-based collective perception under diverse weather conditions.<n>We present a novel multi-task architecture for LiDAR-based collective perception under adverse weather.<n>DenoiseCP-Net integrates voxel-level noise filtering and object detection into a unified sparse backbone.
  arXiv  Detail & Related papers  (2025-07-09T16:05:25Z)
• REHEARSE-3D: A Multi-modal Emulated Rain Dataset for 3D Point Cloud De-raining [0.5668912212306543]
  We release a new, large-scale, multi-modal emulated rain dataset, REHEARSE-3D, to promote research advancements in 3D point cloud de-raining. First, it is the largest point-wise annotated dataset, and second, it is the only one with high-resolution LiDAR data enriched with 4D Radar point clouds. We benchmark raindrop detection and removal in fused LiDAR and 4D Radar point clouds.
  arXiv  Detail & Related papers  (2025-04-30T14:43:38Z)
• WeatherGen: A Unified Diverse Weather Generator for LiDAR Point Clouds via Spider Mamba Diffusion [39.36578688743474]
  3D scene perception demands a large amount of adverse-weather LiDAR data. Yet, the cost of LiDAR data collection presents a significant scaling-up challenge. This paper presents WeatherGen, the first unified diverse-weather LiDAR data diffusion generation framework.
  arXiv  Detail & Related papers  (2025-04-18T09:01:07Z)
• Noise2Score3D: Tweedie's Approach for Unsupervised Point Cloud Denoising [5.888237456794972]
  Noise2Score3D learns the score function of the underlying point cloud distribution directly from noisy data.<n>Our method performs denoising in a single step, avoiding the iterative processes used in existing unsupervised methods.
  arXiv  Detail & Related papers  (2025-03-12T11:28:04Z)
• Noise2Score3D:Unsupervised Tweedie's Approach for Point Cloud Denoising [0.0]
  Noise2Score3D learns the gradient of the underlying point cloud distribution directly from noisy data.<n>Our method performs inference in a single step, avoiding the iterative processes used in existing unsupervised methods.<n>We introduce Total Variation for Point Cloud, a criterion that allows for the estimation of unknown noise parameters.
  arXiv  Detail & Related papers  (2025-02-24T04:23:21Z)
• Integrating Weather Station Data and Radar for Precipitation Nowcasting: SmaAt-fUsion and SmaAt-Krige-GNet [4.475469482534038]
  This study introduces two novel deep learning architectures for precipitation nowcasting. One model extends the SmaAt-UNet framework by incorporating weather station data through a convolutional layer. The other model combines precipitation maps with weather station data processed using Kriging, a geo-statistical method.
  arXiv  Detail & Related papers  (2025-02-22T06:46:04Z)
• SemiDDM-Weather: A Semi-supervised Learning Framework for All-in-one Adverse Weather Removal [57.52777076116241]
  Adverse weather removal aims to restore clear vision under adverse weather conditions. This paper presents a pioneering semi-supervised all-in-one adverse weather removal framework built on the teacher-student network.
  arXiv  Detail & Related papers  (2024-09-29T12:12:22Z)
• M3DM-NR: RGB-3D Noisy-Resistant Industrial Anomaly Detection via Multimodal Denoising [63.39134873744748]
  Existing industrial anomaly detection methods primarily concentrate on unsupervised learning with pristine RGB images. This paper proposes a novel noise-resistant M3DM-NR framework to leverage strong multi-modal discriminative capabilities of CLIP. Extensive experiments show that M3DM-NR outperforms state-of-the-art methods in 3D-RGB multi-modal noisy anomaly detection.
  arXiv  Detail & Related papers  (2024-06-04T12:33:02Z)
• Creating and Leveraging a Synthetic Dataset of Cloud Optical Thickness Measures for Cloud Detection in MSI [3.4764766275808583]
  Cloud formations often obscure optical satellite-based monitoring of the Earth's surface. We propose a novel synthetic dataset for cloud optical thickness estimation. We leverage for obtaining reliable and versatile cloud masks on real data.
  arXiv  Detail & Related papers  (2023-11-23T14:28:28Z)
• LiDAR Data Synthesis with Denoising Diffusion Probabilistic Models [1.1965844936801797]
  Generative modeling of 3D LiDAR data is an emerging task with promising applications for autonomous mobile robots. We present R2DM, a novel generative model for LiDAR data that can generate diverse and high-fidelity 3D scene point clouds. Our method is built upon denoising diffusion probabilistic models (DDPMs), which have shown impressive results among generative model frameworks.
  arXiv  Detail & Related papers  (2023-09-17T12:26:57Z)
• Realistic Noise Synthesis with Diffusion Models [68.48859665320828]
  Deep image denoising models often rely on large amount of training data for the high quality performance. We propose a novel method that synthesizes realistic noise using diffusion models, namely Realistic Noise Synthesize Diffusor (RNSD) RNSD can incorporate guided multiscale content, such as more realistic noise with spatial correlations can be generated at multiple frequencies.
  arXiv  Detail & Related papers  (2023-05-23T12:56:01Z)
• LiDAR Snowfall Simulation for Robust 3D Object Detection [116.10039516404743]
  We propose a physically based method to simulate the effect of snowfall on real clear-weather LiDAR point clouds. Our method samples snow particles in 2D space for each LiDAR line and uses the induced geometry to modify the measurement for each LiDAR beam. We use our simulation to generate partially synthetic snowy LiDAR data and leverage these data for training 3D object detection models that are robust to snowfall.
  arXiv  Detail & Related papers  (2022-03-28T21:48:26Z)
• Fog Simulation on Real LiDAR Point Clouds for 3D Object Detection in Adverse Weather [92.84066576636914]
  This work addresses the challenging task of LiDAR-based 3D object detection in foggy weather. We tackle this problem by simulating physically accurate fog into clear-weather scenes. We are the first to provide strong 3D object detection baselines on the Seeing Through Fog dataset.
  arXiv  Detail & Related papers  (2021-08-11T14:37:54Z)
• Lidar Light Scattering Augmentation (LISA): Physics-based Simulation of Adverse Weather Conditions for 3D Object Detection [60.89616629421904]
  Lidar-based object detectors are critical parts of the 3D perception pipeline in autonomous navigation systems such as self-driving cars. They are sensitive to adverse weather conditions such as rain, snow and fog due to reduced signal-to-noise ratio (SNR) and signal-to-background ratio (SBR)
  arXiv  Detail & Related papers  (2021-07-14T21:10:47Z)
• Scalable Scene Flow from Point Clouds in the Real World [30.437100097997245]
  We introduce a new large scale benchmark for scene flow based on the Open dataset. We show how previous works were bounded based on the amount of real LiDAR data available. We introduce the model architecture FastFlow3D that provides real time inference on the full point cloud.
  arXiv  Detail & Related papers  (2021-03-01T20:56:05Z)
• ePointDA: An End-to-End Simulation-to-Real Domain Adaptation Framework for LiDAR Point Cloud Segmentation [111.56730703473411]
  Training deep neural networks (DNNs) on LiDAR data requires large-scale point-wise annotations. Simulation-to-real domain adaptation (SRDA) trains a DNN using unlimited synthetic data with automatically generated labels. ePointDA consists of three modules: self-supervised dropout noise rendering, statistics-invariant and spatially-adaptive feature alignment, and transferable segmentation learning.
  arXiv  Detail & Related papers  (2020-09-07T23:46:08Z)
• Pseudo-LiDAR Point Cloud Interpolation Based on 3D Motion Representation and Spatial Supervision [68.35777836993212]
  We propose a Pseudo-LiDAR point cloud network to generate temporally and spatially high-quality point cloud sequences. By exploiting the scene flow between point clouds, the proposed network is able to learn a more accurate representation of the 3D spatial motion relationship.
  arXiv  Detail & Related papers  (2020-06-20T03:11:04Z)
• A Nearest Neighbor Network to Extract Digital Terrain Models from 3D Point Clouds [1.6249267147413524]
  We present an algorithm that operates on 3D-point clouds and estimates the underlying DTM for the scene using an end-to-end approach. Our model learns neighborhood information and seamlessly integrates this with point-wise and block-wise global features.
  arXiv  Detail & Related papers  (2020-05-21T15:54:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.