Research map / Point clouds / Segmentation and detection
RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud Segmentation
Jianyun Xu, Ruixiang Zhang, Jian Dou, Yushi Zhu, Jie Sun, Shiliang Pu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add range view to voxel+point fusion (RPV vs PV) (ablation) | RPVNet · SemanticKITTI val | mIoU: 63.8 -> 65.5 | Improved |
| add range view to voxel+point fusion (RPV vs PV) (ablation) | RPVNet · nuScenes val | mIoU: 71.7 -> 73.7 | Improved |
| add point view to voxel view (PV vs V) (ablation) | RPVNet · SemanticKITTI val | mIoU: 63.6 -> 63.8 | Improved |
| add range view to point view (RP vs R) (ablation) | RPVNet · SemanticKITTI val | mIoU: 47.5 -> 50.5 | Improved |
| use gated fusion instead of addition (ablation) | RPVNet · SemanticKITTI val | mIoU: 67.2 -> 68.2 | Improved |
| use gated fusion instead of addition (ablation) | RPVNet · nuScenes val | mIoU: 76.9 -> 77.6 | Improved |
| use gated fusion instead of concatenation (ablation) | RPVNet · SemanticKITTI val | mIoU: 67.4 -> 68.2 | Improved |
| use feature-level multi-view fusion instead of softmax model ensemble (ablation) | RPV · SemanticKITTI val | mIoU: 64.5 -> 68.2 | Improved |
| fusion instead of ensemble for PV (ablation) | PV · SemanticKITTI val | mIoU: 63.9 -> 64.8 | Improved |
| add P-branch to V baseline (ablation) | RPVNet · SemanticKITTI val | mIoU: 64.2 -> 64.8 | Improved |
| add R-branch on top of V+P (ablation) | RPVNet · SemanticKITTI val | mIoU: 64.8 -> 68.2 | Improved |
| add instance cut-mix augmentation (ablation) | RPVNet · SemanticKITTI val | mIoU: 68.2 -> 69.6 | Improved |
Later papers that compared with this method
9 later accepted papers report RPVNet as a baseline in their results tables; 7 of them report a better number on most of the results they share with it.
- Frozen CLIP Transformer Is an Efficient Point Cloud Encoder (AAAI 2024 · better on 1 of 1 shared result)
- Using a Waffle Iron for Automotive Point Cloud Semantic Segmentation (ICCV 2023 · better on 1 of 2 shared results)
- Spherical Transformer for LiDAR-Based 3D Recognition (CVPR 2023 · better on 1 of 1 shared result)
- Efficient LiDAR Point Cloud Oversegmentation Network (ICCV 2023 · better on 0 of 1 shared result)
- ProtoTransfer: Cross-Modal Prototype Transfer for Point Cloud Segmentation (ICCV 2023 · better on 1 of 1 shared result)
- Rethinking Range View Representation for LiDAR Segmentation (ICCV 2023 · better on 1 of 1 shared result)
- Clustering based Point Cloud Representation Learning for 3D Analysis (ICCV 2023 · better on 1 of 1 shared result)
- Efficient Point Cloud Segmentation with Geometry-Aware Sparse Networks (ECCV 2022 · better on 3 of 3 shared results)
1 more not listed.
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- PolarNet — PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation (CVPR 2020) · better on 2 of 2 shared results
- RandLANet — RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds (CVPR 2020) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentation (CVPR 2022 · similarity 0.91)
- Deep FusionNet for Point Cloud Semantic Segmentation (ECCV 2020 · similarity 0.90)
- Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation (CVPR 2021 · similarity 0.90)
- Voxel or Pillar: Exploring Efficient Point Cloud Representation for 3D Object Detection (AAAI 2024 · similarity 0.90)
- GeoAuxNet: Towards Universal 3D Representation Learning for Multi-sensor Point Clouds (CVPR 2024 · similarity 0.89)
- LiDAR-Net: A Real-scanned 3D Point Cloud Dataset for Indoor Scenes (CVPR 2024 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
