| LSK3DNet: Towards Effective and Efficient 3D Perception with Large Sparse Kernels | ✓ Link | 75.6% | 70.2% | | LSK3DNet | 2024-03-22 |
| Point Transformer V3: Simpler, Faster, Stronger | ✓ Link | 75.5% | 72.3% | | PPT+PTv3 | 2023-12-15 |
| UniSeg: A Unified Multi-Modal LiDAR Segmentation Network and the OpenPCSeg Codebase | ✓ Link | 75.2% | 71.3% | | UniSeg | 2023-09-11 |
| Spherical Transformer for LiDAR-based 3D Recognition | ✓ Link | 74.8% | 67.8% | | SphereFormer | 2023-03-22 |
| DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation | ✓ Link | 74.4% | 69.0% | | DITR | 2025-03-24 |
| FRNet: Frustum-Range Networks for Scalable LiDAR Segmentation | ✓ Link | 73.3% | 68.7% | | FRNet | 2023-12-07 |
| Rethinking Range View Representation for LiDAR Segmentation | | 73.3% | 67.6% | | RangeFormer | 2023-03-09 |
| 2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds | ✓ Link | 72.9% | 69.3% | | 2DPASS | 2022-07-10 |
| Point Transformer V2: Grouped Vector Attention and Partition-based Pooling | ✓ Link | 72.6% | 70.3% | | PTv2 | 2022-10-11 |
| Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentation | | 71.2% | | | PVKD | 2022-06-05 |
| (AF)2-S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Network | | 70.8% | 74.2% | | AF2S3Net | 2021-02-08 |
| Using a Waffle Iron for Automotive Point Cloud Semantic Segmentation | ✓ Link | 70.8% | 68.0% | | WaffleIron | 2023-01-24 |
| Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation | ✓ Link | 68.9% | 64.3% | | Cylinder3D | 2020-11-19 |
| Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution | ✓ Link | 66.4% | 64.7% | | SPVNAS | 2020-07-31 |
| Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion | ✓ Link | 66.0% | | | JS3C-Net | 2020-12-07 |
| GFNet: Geometric Flow Network for 3D Point Cloud Semantic Segmentation | ✓ Link | 65.4% | | | GFNet | 2022-07-06 |
| KPRNet: Improving projection-based LiDAR semantic segmentation | ✓ Link | 63.1% | | | KPRNet | 2020-07-24 |
| TORNADO-Net: mulTiview tOtal vaRiatioN semAntic segmentation with Diamond inceptiOn module | | 63.1% | | | TORNADONet-HiRes | 2020-08-24 |
| Number-Adaptive Prototype Learning for 3D Point Cloud Semantic Segmentation | | 61.6% | | | NAPL | 2022-10-18 |
| Meta-RangeSeg: LiDAR Sequence Semantic Segmentation Using Multiple Feature Aggregation | ✓ Link | 61.0% | | | Meta-RangeSeg | 2022-02-27 |
| Semantic Segmentation for Real Point Cloud Scenes via Bilateral Augmentation and Adaptive Fusion | ✓ Link | 59.9% | | | BAAF-Net | 2021-03-12 |
| SalsaNext: Fast, Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Driving | ✓ Link | 59.5% | | | SalsaNext | 2020-03-07 |
| KPConv: Flexible and Deformable Convolution for Point Clouds | ✓ Link | 58.8% | | | KPConv | 2019-04-18 |
| PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation | ✓ Link | 57.2% | | | PolarNet | 2020-03-31 |
| FPS-Net: A Convolutional Fusion Network for Large-Scale LiDAR Point Cloud Segmentation | ✓ Link | 57.1% | | | FPS-Net | 2021-03-01 |
| SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation | ✓ Link | 55.9% | | | SqueezeSegV3 | 2020-04-03 |
| 3D-MiniNet: Learning a 2D Representation from Point Clouds for Fast and Efficient 3D LIDAR Semantic Segmentation | ✓ Link | 55.8% | | | 3D-MiniNet | 2020-02-25 |
| Multi Projection Fusion for Real-time Semantic Segmentation of 3D LiDAR Point Clouds | | 55.5% | | | MPF | 2020-11-03 |
| Multi-scale Interaction for Real-time LiDAR Data Segmentation on an Embedded Platform | ✓ Link | 55.2% | | | MINet | 2020-08-20 |
| RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds | ✓ Link | 53.9% | | | RandLA-Net | 2019-11-25 |
| FG-Net: Fast Large-Scale LiDAR Point Clouds Understanding Network Leveraging Correlated Feature Mining and Geometric-Aware Modelling | ✓ Link | 53.8% | | | FG-Net | 2020-12-17 |
| LatticeNet: Fast Point Cloud Segmentation Using Permutohedral Lattices | ✓ Link | 52.9% | | | LatticeNet | 2019-12-12 |
| RangeNet++: Fast and Accurate LiDAR Semantic Segmentation | ✓ Link | 52.2% | | | RangeNet++ | 2019-11-04 |
| SemanticKITTI: A Dataset for Semantic Scene Understanding of LiDAR Sequences | ✓ Link | 49.9% | | | Darknet53 | 2019-04-02 |
| SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud | ✓ Link | 39.7% | | | SqueezeSegV2 | 2018-09-22 |
| Tangent Convolutions for Dense Prediction in 3D | ✓ Link | 35.9% | | | TangentConv | 2018-07-06 |
| SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloud | ✓ Link | 29.5% | | | SqueezeSeg | 2017-10-19 |
| PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space | ✓ Link | 20.1% | | | PointNet++ | 2017-06-07 |
| SPLATNet: Sparse Lattice Networks for Point Cloud Processing | ✓ Link | 18.4% | | | SPLATNet | 2018-02-22 |
| Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs | ✓ Link | 17.4% | | | SPGraph | 2017-11-27 |
| PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation | ✓ Link | 14.6% | | | PointNet | 2016-12-02 |
| Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training | ✓ Link | | 71.4% | | PPT+SparseUNet | 2023-08-18 |
| OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation | ✓ Link | | 70.6% | | OA-CNNs | 2024-03-21 |
| Less is More: Reducing Task and Model Complexity for 3D Point Cloud Semantic Segmentation | ✓ Link | | | 58.4 | LiM3D | 2023-03-20 |
| Less is More: Reducing Task and Model Complexity for 3D Point Cloud Semantic Segmentation | ✓ Link | | | 57.2 | LiM3D+SDSC | 2023-03-20 |