A Preprocessing and Postprocessing Voxel-based Method for LiDAR Semantic Segmentation Improvement in Long Distance
Not on the map. Why?
Abstract (arXiv)
In recent years considerable research in LiDAR semantic segmentation was conducted, introducing several new state of the art models. However, most research focuses on single-scan point clouds, limiting performance especially in long distance outdoor scenarios, by omitting time-sequential information. Moreover, varying-density and occlusions constitute significant challenges in single-scan approaches. In this paper we propose a LiDAR point cloud preprocessing and postprocessing method. This multi-stage approach, in conjunction with state of the art models in a multi-scan setting, aims to solve those challenges. We demonstrate the benefits of our method through quantitative evaluation with the given models in single-scan settings. In particular, we achieve significant improvements in mIoU performance of over 5 percentage point in medium range and over 10 percentage point in far range. This is essential for 3D semantic scene understanding in long distance as well as for applications where offline processing is permissible.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 29 of its 33 references that are in the map. First posted on arXiv 16 May 2024.
Builds on
29 of 33 references.
References · 29
- 2017Attention Is All You Needcited by 59,932
- 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
- 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
- 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
- 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
- 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
- 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
- 2020Searching Efficient 3D Architectures with Sparse Point-Voxel Convolutioncited by 422
- 2020Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentationcited by 388
- 2022Point Transformer V2: Grouped Vector Attention and Partition-based Poolingcited by 384
- 2021Voxel Transformer for 3D Object Detectioncited by 247
- 2018SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloudcited by 228
17 more
- 2017Submanifold Sparse Convolutional Networkscited by 223
- 2021Embracing Single Stride 3D Object Detector with Sparse Transformercited by 193
- 2022Stratified Transformer for 3D Point Cloud Segmentationcited by 166
- 2022KISS-ICP: In Defense of Point-to-Point ICP -- Simple, Accurate, and Robust Registration If Done the Right Waycited by 132
- 2023Rethinking Range View Representation for LiDAR Segmentationcited by 126
- 2023Spherical Transformer for LiDAR-based 3D Recognitioncited by 124
- 2020Deep Learning for LiDAR Point Clouds in Autonomous Driving: A Reviewcited by 114
- 2020Cylinder3D: An Effective 3D Framework for Driving-scene LiDAR Semantic Segmentationcited by 112
- 2022SWFormer: Sparse Window Transformer for 3D Object Detection in Point Cloudscited by 92
- 2023Using a Waffle Iron for Automotive Point Cloud Semantic Segmentationcited by 53
- 2022Dynamic 3D Scene Analysis by Point Cloud Accumulationcited by 47
- 2021LiDAR-based Recurrent 3D Semantic Segmentation with Temporal Memory Alignmentcited by 26
- 2022Meta-RangeSeg: LiDAR Sequence Semantic Segmentation Using Multiple Feature Aggregationcited by 23
- 2023MarS3D: A Plug-and-Play Motion-Aware Model for Semantic Segmentation on Multi-Scan 3D Point Cloudscited by 19
- 2023Building Volumetric Beliefs for Dynamic Environments Exploiting Map-Based Moving Object Segmentationcited by 15
- 2022Abstract Flow for Temporal Semantic Segmentation on the Permutohedral Latticecited by 9
- 2022Sequential Point Clouds: A Surveycited by 5
Built on by
Not cited yet.