| DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation | ✓ Link | 80.5 | 79.7 | DITR | 2025-03-24 |
| Sonata: Self-Supervised Learning of Reliable Point Representations | ✓ Link | 79.4 | | Sonata + PTv3 | 2025-03-20 |
| ARKit LabelMaker: A New Scale for Indoor 3D Scene Understanding | ✓ Link | 79.1 | 79.8 | PTv3 ARKit LabelMaker | 2024-10-17 |
| Point Transformer V3: Simpler, Faster, Stronger | ✓ Link | 78.6 | 79.4 | PTv3 + PPT | 2023-12-15 |
| BFANet: Revisiting 3D Semantic Segmentation with Boundary Feature Analysis | ✓ Link | 78.0 | | BFANet | 2025-03-16 |
| ODIN: A Single Model for 2D and 3D Segmentation | ✓ Link | 77.8 | 74.4 | ODIN | 2024-01-04 |
| HybridTM: Combining Transformer and Mamba for 3D Semantic Segmentation | | 77.8 | | HybridTM | 2025-07-24 |
| Pamba: Enhancing Global Interaction in Point Clouds via State Space Model | | 77.6 | | Pamba | 2024-06-25 |
| Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding | ✓ Link | 77.5 | 77.9 | Swin3D-L | 2023-04-14 |
| PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm | ✓ Link | 77.0 | 78.5 | PonderV2 + SparseUNet | 2023-10-12 |
| Serialized Point Mamba: A Serialized Point Cloud Mamba Segmentation Model | | 76.8 | | Serialized Piont Mamba | 2024-07-17 |
| OneFormer3D: One Transformer for Unified Point Cloud Segmentation | ✓ Link | 76.6 | | OneFormer3D | 2023-11-24 |
| Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training | ✓ Link | 76.4 | 76.6 | PPT + SparseUNet | 2023-08-18 |
| KPConvX: Modernizing Kernel Point Convolution with Kernel Attention | ✓ Link | 76.3 | | KPConvX-L | 2024-05-21 |
| PT-WNO: Point Transformer with Wavelet Neural Operator for 3D Point Cloud Semantic Segmentation | | 76.19 | | PT-WNO | 2026-06-09 |
| AVS-Net: Point Sampling with Adaptive Voxel Size for 3D Scene Understanding | ✓ Link | 76.1 | | AVS-Net | 2024-02-27 |
| OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation | ✓ Link | 76.1 | 75.6 | OA-CNNs | 2024-03-21 |
| Decoupled Local Aggregation for Point Cloud Learning | ✓ Link | 75.9 | | DeLA | 2023-08-31 |
| OctFormer: Octree-based Transformers for 3D Point Clouds | ✓ Link | 75.7 | 76.6 | OctFormer | 2023-05-04 |
| LSK3DNet: Towards Effective and Efficient 3D Perception with Large Sparse Kernels | ✓ Link | 75.7 | 75.5 | LSK3DNet | 2024-03-22 |
| Masked Scene Contrast: A Scalable Framework for Unsupervised 3D Representation Learning | ✓ Link | 75.5 | | MSC + SparseUNet | 2023-03-24 |
| Point Transformer V2: Grouped Vector Attention and Partition-based Pooling | ✓ Link | 75.4 | 75.2 | PTv2 | 2022-10-11 |
| PointHR: Exploring High-Resolution Architectures for 3D Point Cloud Segmentation | ✓ Link | 75.4 | 76.6 | PointHR | 2023-10-11 |
| A Unified Query-based Paradigm for Point Cloud Understanding | ✓ Link | 75.3 | 74.3 | EQ-Net | 2022-03-02 |
| Stratified Transformer for 3D Point Cloud Segmentation | ✓ Link | 74.3 | 73.7 | StratifiedFormer | 2022-03-28 |
| O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis | ✓ Link | 74.0 | 76.2 | O-CNN | 2017-12-05 |
| Bidirectional Projection Network for Cross Dimension Scene Understanding | ✓ Link | 73.9 | 74.9 | BPNet | 2021-03-26 |
| Mix3D: Out-of-Context Data Augmentation for 3D Scenes | ✓ Link | 73.6 | 78.1 | Mix3D | 2021-10-05 |
| Efficient Point Cloud Processing with High-Dimensional Positional Encoding and Non-Local MLPs | ✓ Link | 73.3 | | HPENet V2-XL | 2026-03-04 |
| 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks | ✓ Link | 72.2 | 73.4 | MinkowskiNet | 2019-04-18 |
| Efficient Point Cloud Processing with High-Dimensional Positional Encoding and Non-Local MLPs | ✓ Link | 71.4 | | HPENet V2-L | 2026-03-04 |
| Efficient Point Cloud Processing with High-Dimensional Positional Encoding and Non-Local MLPs | ✓ Link | 70.6 | | HPENet V2-B | 2026-03-04 |
| 3D Semantic Segmentation with Submanifold Sparse Convolutional Networks | ✓ Link | 69.3 | 72.5 | SparseConvNet | 2017-11-28 |
| KPConv: Flexible and Deformable Convolution for Point Clouds | ✓ Link | 69.2 | 68.0 | KpConv | 2019-04-18 |
| PanopticNDT: Efficient and Robust Panoptic Mapping | ✓ Link | 68.39 | 68.1 | PanopticNDT (10cm) | 2023-09-24 |
| Efficient Point Cloud Processing with High-Dimensional Positional Encoding and Non-Local MLPs | ✓ Link | 66.3 | | HPENet V2-S | 2026-03-04 |
| PointConv: Deep Convolutional Networks on 3D Point Clouds | ✓ Link | 61.0 | 55.6 | PointConv | 2018-11-17 |
| PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space | ✓ Link | 53.5 | 33.9 | PointNet++ | 2017-06-07 |
| Virtual Multi-view Fusion for 3D Semantic Segmentation | ✓ Link | | 74.6 | VMVF | 2020-07-26 |
| FG-Net: Fast Large-Scale LiDAR Point Clouds Understanding Network Leveraging Correlated Feature Mining and Geometric-Aware Modelling | ✓ Link | | 69.0 | FG-Net | 2020-12-17 |
| Learning Inner-Group Relations on Point Clouds | ✓ Link | | 68.2 | RPNet | 2021-08-27 |
| Similarity-Aware Fusion Network for 3D Semantic Segmentation | ✓ Link | | 65.4 | SAFNet | 2021-07-04 |
| TextureNet: Consistent Local Parametrizations for Learning from High-Resolution Signals on Meshes | ✓ Link | | 56.6 | TextureNet | 2018-11-30 |
| PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things | | | 52.9 | PanopticFusion | 2019-03-04 |
| 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation | ✓ Link | | 48.4 | 3DMV | 2018-03-28 |
| PointCNN: Convolution On X-Transformed Points | ✓ Link | | 45.8 | PointCNN | 2018-12-01 |
| Fully-Convolutional Point Networks for Large-Scale Point Clouds | ✓ Link | | 44.7 | FCPN | 2018-08-21 |
| PFCNN: Convolutional Neural Networks on 3D Surfaces Using Parallel Frames | ✓ Link | | 44.2 | SurfaceConvPF | 2018-08-15 |
| Tangent Convolutions for Dense Prediction in 3D | ✓ Link | | 44.2 | Tangent Convolutions | 2018-07-06 |
| SPLATNet: Sparse Lattice Networks for Point Cloud Processing | ✓ Link | | 39.3 | SPLAT Net | 2018-02-22 |
| ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes | ✓ Link | | 30.6 | ScanNet | 2017-02-14 |
| Volume Transformer: Revisiting Vanilla Transformers for 3D Scene Understanding | ✓ Link | | 80.5 | Volt-B | 2026-04-21 |
| TTT-KD: Test-Time Training for 3D Semantic Segmentation through Knowledge Distillation from Foundation Models | | | 77.6 | TTT-KD | 2024-03-18 |
| Point Neighborhood Embeddings | | | 75.5 | PNE | 2023-10-03 |
| Towards Deeper and Better Multi-view Feature Fusion for 3D Semantic Segmentation | | | 75.2 | DMF-Net | 2022-12-13 |
| VMNet: Voxel-Mesh Network for Geodesic-Aware 3D Semantic Segmentation | | | 74.6 | VMNet | 2021-07-29 |
| Retro-FPN: Retrospective Feature Pyramid Network for Point Cloud Semantic Segmentation | ✓ Link | | 74.4 | Retro-FPN | 2023-08-18 |
| LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs | | | 73.9 | LargeKernel3D | 2022-06-21 |
| Contrastive Boundary Learning for Point Cloud Segmentation | ✓ Link | | 70.5 | contrastBoundary | 2022-03-10 |
| Omni-supervised Point Cloud Segmentation via Gradual Receptive Field Component Reasoning | ✓ Link | | 70.2 | RFCR | 2021-05-21 |
| JSENet: Joint Semantic Segmentation and Edge Detection Network for 3D Point Clouds | ✓ Link | | 69.9 | JSENet | 2020-07-14 |
| Mesh Convolution with Continuous Filters for 3D Surface Parsing | | | 69.2 | PicassoNet-II | 2021-12-03 |
| The Devils in the Point Clouds: Studying the Robustness of Point Cloud Convolutions | | | 67.6 | VI-PointConv | 2021-01-19 |
| DeepLA-Net: Very Deep Local Aggregation Networks for Point Cloud Analysis | | | 77.2 | DeepLA-120 | 2025-06-11 |
| PointConvFormer: Revenge of the Point-based Convolution | | | 74.9 | PointConvFormer | 2022-08-04 |
| One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation | | | 69.3 | One-Thing-One-Click | 2021-04-06 |