| Sonata: Self-Supervised Learning of Reliable Point Representations | ✓ Link | 76.0 | 81.6 | 93.0 | | | Sonata + PTv3 | 2025-03-20 |
| OmniVec: Learning robust representations with cross modal sharing | | 75.9 | | | | | OmniVec | 2023-11-07 |
| DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation | ✓ Link | 75.0 | | | | | D-DITR | 2025-03-24 |
| Point Transformer V3: Simpler, Faster, Stronger | ✓ Link | 74.7 | 80.1 | 92.0 | | | PTv3 + PPT | 2023-12-15 |
| Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding | ✓ Link | 74.5 | 80.5 | 92.7 | | N/A | Swin3D-L | 2023-04-14 |
| Decoupled Local Aggregation for Point Cloud Learning | ✓ Link | 74.1 | 80.0 | 92.2 | | 7.0M | DeLA | 2023-08-31 |
| DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation | ✓ Link | 74.1 | | | | | DITR | 2025-03-24 |
| Beyond local patches: Preserving global–local interactions by enhancing self-attention via 3D point cloud tokenization | | 73.6 | 80.2 | 93.0 | | | Ours | 2024-11-01 |
| ConDaFormer: Disassembled Transformer with Local Structure Enhancement for 3D Point Cloud Understanding | ✓ Link | 73.5 | 78.9 | 92.4 | | | ConDaFormer | 2023-12-18 |
| A Large-Scale Network Construction and Lightweighting Method for Point Cloud Semantic Segmentation | ✓ Link | 73.5 | 78.7 | 92.0 | 24.2G | 31.2M | LPFP(Point Transformer*) | 2024-03-21 |
| KPConvX: Modernizing Kernel Point Convolution with Kernel Attention | ✓ Link | 73.5 | 78.7 | 91.7 | | | KPConvX-L | 2024-05-21 |
| Pamba: Enhancing Global Interaction in Point Clouds via State Space Model | | 73.5 | | | | | Pamba | 2024-06-25 |
| Subspace Prototype Guidance for Mitigating Class Imbalance in Point Cloud Semantic Segmentation | ✓ Link | 73.3 | 79.5 | 91.9 | | | SPG(PTv2) | 2024-08-20 |
| PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm | ✓ Link | 73.2 | 79.0 | 92.2 | | | PonderV2 + SparseUNet | 2023-10-12 |
| PointHR: Exploring High-Resolution Architectures for 3D Point Cloud Segmentation | ✓ Link | 73.2 | 78.7 | 91.8 | | | PointHR | 2023-10-11 |
| Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training | ✓ Link | 72.7 | 78.2 | 91.5 | | N/A | PPT + SparseUNet | 2023-08-18 |
| SAT: Size-Aware Transformer for 3D Point Cloud Semantic Segmentation | | 72.6 | 78.8 | | | N/A | SAT (FAT) | 2023-01-17 |
| Point Transformer V2: Grouped Vector Attention and Partition-based Pooling | ✓ Link | 72.6 | 78.0 | 91.6 | | N/A | PTv2 | 2022-10-11 |
| []() | | 72.6 | | | | | PT + ERDA | |
| PointVector: A Vector Representation In Point Cloud Analysis | ✓ Link | 72.3 | 78.1 | 91 | | | PointVector-XL | 2022-05-21 |
| Window Normalization: Enhancing Point Cloud Understanding by Unifying Inconsistent Point Densities | ✓ Link | 72.2 | 78.2 | 91.4 | | N/A | WindowNorm+StratifiedTransformer | 2022-12-05 |
| Diffusion Unit: Interpretable Edge Enhancement and Suppression Learning for 3D Point Cloud Segmentation | ✓ Link | 72.2 | 78.1 | 91.3 | | 8.1M | Diffusion Unit | 2022-09-20 |
| Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts | ✓ Link | 72.2 | | | | | CSC+MinkUNet | 2020-12-16 |
| Stratified Transformer for 3D Point Cloud Segmentation | ✓ Link | 72.0 | 78.1 | 91.5 | | 8.0M | StratifiedTransformer | 2022-03-28 |
| Contrastive Boundary Learning for Point Cloud Segmentation | ✓ Link | 71.6 | 77.9 | 91.2 | | N/A | PointTransformer+CBL | 2022-03-10 |
| Window Normalization: Enhancing Point Cloud Understanding by Unifying Inconsistent Point Densities | ✓ Link | 71.4 | 77.9 | 91.1 | | N/A | WindowNorm+PointTransformer | 2022-12-05 |
| PointMixer: MLP-Mixer for Point Cloud Understanding | ✓ Link | 71.4 | 77.4 | | | 6.5M | PointMixer | 2021-11-22 |
| Meta Architecture for Point Cloud Analysis | ✓ Link | 71.3±0.7 | | | | N/A | PointMetaBase-XXL | 2022-11-26 |
| PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies | ✓ Link | 71.1 | 77.2 | 91.0 | | 41.6M | PointNeXt | 2022-06-09 |
| Self-positioning Point-based Transformer for Point Cloud Understanding | ✓ Link | 70.8 | 76.4 | 90.7 | | N/A | SPoTr | 2023-03-29 |
| Serialized Point Mamba: A Serialized Point Cloud Mamba Segmentation Model | | 70.6 | | | | | Serialized Piont Mamba | 2024-07-17 |
| Point Transformer | ✓ Link | 70.4 | 76.5 | 90.8 | | 7.8M | PointTransformer | 2020-12-16 |
| LCPFormer: Towards Effective 3D Point Cloud Analysis via Local Context Propagation in Transformers | ✓ Link | 70.2 | 76.8 | 90.8 | | N/A | LCPFormer | 2022-10-23 |
| Exploiting Local Geometry for Feature and Graph Construction for Better 3D Point Cloud Processing with Graph Neural Networks | | 69.4 | | 89.4 | | | GeomGCNN | 2021-03-28 |
| Efficient 3D Semantic Segmentation with Superpoint Transformer | ✓ Link | 68.9 | 77.3 | 89.5 | | 212K | Superpoint Transformer | 2023-06-13 |
| Surface Representation for Point Clouds | ✓ Link | 68.9 | 76.0 | 90.2 | 1.04G | 0.97M | RepSurf-U | 2022-05-11 |
| CGA-Net: Category Guided Aggregation for Point Cloud Semantic Segmentation | ✓ Link | 68.6 | | | | N/A | CGA-Net | 2021-06-19 |
| Scalable 3D Panoptic Segmentation As Superpoint Graph Clustering | ✓ Link | 68.1 | | | | 0.21 | SuperCluster | 2024-01-12 |
| MKConv: Multidimensional Feature Representation for Point Cloud Analysis | | 67.7 | 75.1 | 89.6 | | | MKConv | 2021-07-27 |
| PatchFormer: An Efficient Point Transformer with Patch Attention | | 67.3 | | | | N/A | PatchFormer | 2021-10-30 |
| Deep FusionNet for Point Cloud Semantic Segmentation | | 67.2 | 72.3 | | | N/A | FusionNet | |
| KPConv: Flexible and Deformable Convolution for Point Clouds | ✓ Link | 67.1 | 72.8 | | | 14.1M | KPConv | 2019-04-18 |
| ASSANet: An Anisotropic Separable Set Abstraction for Efficient Point Cloud Representation Learning | ✓ Link | 66.8 | | | | N/A | ASSANet | 2021-10-20 |
| Semantic Segmentation for Real Point Cloud Scenes via Bilateral Augmentation and Adaptive Fusion | ✓ Link | 65.4 | 73.1 | 88.9 | | N/A | BAAF-Net | 2021-03-12 |
| 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks | ✓ Link | 65.4 | 71.7 | | | 37.9M | MinkowskiNet | 2019-04-18 |
| Virtual Multi-view Fusion for 3D Semantic Segmentation | ✓ Link | 65.38 | | | | N/A | VMVF | 2020-07-26 |
| SCF-Net: Learning Spatial Contextual Features for Large-Scale Point Cloud Segmentation | ✓ Link | 63.7 | 71.8 | 87.2 | | N/A | SCF-Net | 2021-06-19 |
| MuGNet: Multi-Resolution Graph Neural Network for Large-Scale Pointcloud Segmentation | ✓ Link | 63.5 | | 88.1 | | N/A | MuG-Net | 2020-11-16 |
| Hierarchical Point-Edge Interaction Network for Point Cloud Semantic Segmentation | | 61.85 | 68.3 | 87.18 | | N/A | HPEIN | 2019-09-23 |
| Point Cloud Oversegmentation with Graph-Structured Deep Metric Learning | ✓ Link | 61.7 | 68.2 | 87.9 | | 290K | SSP+SPG | 2019-04-03 |
| Dilated Point Convolutions: On the Receptive Field Size of Point Convolutions on 3D Point Clouds | ✓ Link | 61.28 | | | | N/A | DPC | 2019-07-28 |
| Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs | ✓ Link | 58.04 | 66.5 | 86.38 | | 280K | SPG | 2017-11-27 |
| Point Transformer | ✓ Link | 57.3 | | | | N/A | PointCNN | 2020-12-16 |
| DeepGCNs: Making GCNs Go as Deep as CNNs | ✓ Link | 52.49 | | | | N/A | DeepGCN | 2019-10-15 |
| SEGCloud: Semantic Segmentation of 3D Point Clouds | | 48.9 | 57.4 | | | N/A | SegCloud | 2017-10-20 |
| Point Transformer | ✓ Link | 41.1 | | | | N/A | PointNet | 2020-12-16 |
| Deep Parametric Continuous Convolutional Neural Networks | | | 67.0 | | | N/A | PCCN | 2021-01-17 |
| Tangent Convolutions for Dense Prediction in 3D | ✓ Link | | 62.2 | | | N/A | TangentConv | 2018-07-06 |
| PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation | ✓ Link | | 49.0 | | | N/A | PointNet | 2016-12-02 |
| PointWeb: Enhancing Local Neighborhood Features for Point Cloud Processing | ✓ Link | | | 87.0 | | N/A | PointWeb | 2019-06-01 |
| PointCNN: Convolution On X-Transformed Points | ✓ Link | | | 85.9 | | N/A | PointCNN | 2018-12-01 |