Research map / Point clouds / Segmentation and detection
2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds
Xu Yan, Jiantao Gao, Chaoda Zheng, Chao Zheng, Ruimao Zhang, Shuguang Cui, Zhen Li
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 KL-divergence alignment between 2D-3D features only (ablation) | 3D baseline · SemanticKITTI val | mIoU: 65.58 -> 66.34 | Improved |
| add 2D-3D modality fusion at each distillation scale (ablation) | baseline + KL · SemanticKITTI val | mIoU: 66.34 -> 69.13 | Improved |
| add the 2D learner (ablation) | baseline + KL + fusion · SemanticKITTI val | mIoU: 69.13 -> 69.32 | Improved |
| use MSFSKD instead of xMUDA cross-modal alignment (ablation) | 2DPASS · SemanticKITTI val | mIoU: 67.88 -> 69.32 | Improved |
| use MSFSKD instead of pure KD (Hinton) (ablation) | 2DPASS · SemanticKITTI val | mIoU: 66.34 -> 69.32 | Improved |
| train MinkowskiNet with 2DPASS | MinkowskiNet · SemanticKITTI val | mIoU: 63.1 -> 66.2 | Improved |
| train SPVCNN with 2DPASS | SPVCNN · SemanticKITTI val | mIoU: 63.8 -> 66.9 | Improved |
| add 2DPASS to the 3D baseline on SemanticKITTI test single scan | 3D baseline · SemanticKITTI test (single scan) | mIoU: 67.4 -> 72.9 | Improved |
| add 2DPASS to the baseline on NuScenes test | 3D baseline · NuScenes test | mIoU: 77.6 -> 80.8 | Improved |
| add 2DPASS to the baseline on NuScenes val | 3D baseline · NuScenes val | mIoU: 76.2 -> 79.4 | Improved |
| add PointPainting 2D logits as 3D input instead of distillation (ablation) | 3D network · NuScenes val | mIoU: 76.56 | No clear effect |
| use 2DPASS (light) instead of multi-sensor inference (ablation) | 3D baseline (light) · NuScenes val | mIoU: 76.04 -> 78.87 | Improved |
Later papers that compared with this method
12 later accepted papers report 2DPASS as a baseline in their results tables; 10 of them report a better number on most of the results they share with it.
- Image-to-Point Cloud Feature Back-Projection for Multimodal Training of 3D Semantic Segmentation (CVPR 2026 · better on 1 of 1 shared result)
- RAPiD-Seg: Range-Aware Pointwise Distance Distribution Networks for 3D LiDAR Segmentation (ECCV 2024 · better on 2 of 2 shared results)
- EPMF: Efficient Perception-Aware Multi-Sensor Fusion for 3D Semantic Segmentation (TPAMI 2024 · better on 2 of 2 shared results)
- TASeg: Temporal Aggregation Network for LiDAR Semantic Segmentation (CVPR 2024 · better on 1 of 1 shared result)
- LinNet: Linear Network for Efficient Point Cloud Representation Learning (NeurIPS 2024 · better on 0 of 1 shared result)
- SFPNet: Sparse Focal Point Network for Semantic Segmentation on General LiDAR Point Clouds (ECCV 2024 · better on 1 of 1 shared result)
- ProtoTransfer: Cross-Modal Prototype Transfer for Point Cloud Segmentation (ICCV 2023 · better on 2 of 3 shared results)
- Spherical Transformer for LiDAR-Based 3D Recognition (CVPR 2023 · better on 2 of 2 shared results)
4 more not listed.
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- RPVNet — RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud Segmentation (ICCV 2021) · better on 2 of 2 shared results
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
- Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR-Based Perception (TPAMI 2021 · similarity 0.90)
- MFINet: Multi-view Fusion and 2D–3D Interaction Enhancement for Real-Time LiDAR Semantic Segmentation (AAAI 2026 · similarity 0.90)
- PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation (CVPR 2020 · similarity 0.90)
- SemanticKITTI: A Dataset for Semantic Scene Understanding of LiDAR Sequences (ICCV 2019 · similarity 0.90)
- Walking Your LiDOG: A Journey Through Multiple Domains for LiDAR Semantic Segmentation (ICCV 2023 · similarity 0.90)
- PC-BEV: An Efficient Polar-Cartesian BEV Fusion Framework for LiDAR Semantic Segmentation (AAAI 2025 · 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.
