| AQ3D: Adaptive Query Transformer for 3D Instance Segmentation | ✓ Link | 83.4 | | 65.6 | | AQ3D | 2026-08-31 |
| Volume Transformer: Revisiting Vanilla Transformers for 3D Scene Understanding | ✓ Link | 82.7 | | | | Volt-B + SPFormer | 2026-04-21 |
| Relation3D : Enhancing Relation Modeling for Point Cloud Instance Segmentation | ✓ Link | 81.6 | 90.1 | 62.2 | | Relation3D | 2025-01-01 |
| Spherical Mask: Coarse-to-Fine 3D Point Cloud Instance Segmentation with Spherical Representation | ✓ Link | 81.2 | 87.5 | 61.6 | | Spherical Mask | 2023-12-18 |
| Beyond the Final Layer: Hierarchical Query Fusion Transformer with Agent-Interpolation Initialization for 3D Instance Segmentation | | 81.0 | 88.2 | 60.6 | | BFL | 2025-02-06 |
| OneFormer3D: One Transformer for Unified Point Cloud Segmentation | ✓ Link | 80.1 | 89.6 | 56.6 | | OneFromer3D | 2023-11-24 |
| SGIFormer: Semantic-guided and Geometric-enhanced Interleaving Transformer for 3D Instance Segmentation | ✓ Link | 79.9 | | | | InsSSM | 2024-07-16 |
| MSTA3D: Multi-scale Twin-attention for 3D Instance Segmentation | | 79.5 | 87.9 | 56.9 | 74.1 | MSTA3D | 2024-11-04 |
| Query Refinement Transformer for 3D Instance Segmentation | | 78.7 | 87.4 | 58.3 | | QueryFormer | 2023-01-01 |
| Mask3D: Mask Transformer for 3D Semantic Instance Segmentation | ✓ Link | 78.0 | 87.0 | 55.2 | | Mask3D | 2022-10-06 |
| Superpoint Transformer for 3D Scene Instance Segmentation | ✓ Link | 77.0 | | 54.9 | | SPFormer | 2022-11-28 |
| ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution | ✓ Link | 76.3 | 84.5 | 55.9 | | ISBNet | 2023-03-01 |
| SoftGroup for 3D Instance Segmentation on Point Clouds | ✓ Link | 76.1 | 86.5 | 50.4 | | SoftGroup | 2022-03-03 |
| Top-Down Beats Bottom-Up in 3D Instance Segmentation | | 75.1 | 87.5 | 48.9 | | TD3D | 2023-02-06 |
| Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise Binarization | ✓ Link | 74.7 | 82.5 | 57.3 | | PBNet | 2022-07-22 |
| 3D Instances as 1D Kernels | ✓ Link | 71.8 | | 53.2 | | DKNet | 2022-07-15 |
| ODIN: A Single Model for 2D and 3D Segmentation | ✓ Link | 71.0 | 83.6 | 50.0 | | ODIN | 2024-01-04 |
| Hierarchical Aggregation for 3D Instance Segmentation | ✓ Link | 69.9 | | 45.7 | | HAIS | 2021-08-05 |
| Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networks | ✓ Link | 69.8 | | 50.6 | | SSTNet | 2021-08-17 |
| TAMM: TriAdapter Multi-Modal Learning for 3D Shape Understanding | ✓ Link | 68.0 | | | | TAMM | 2024-02-28 |
| SAMosaic3D: Modular Scene Assembly for Real-Time 3D Segment Anything | | 67.7 | | | | SAMosaic3D (Ours) dagger | 2026-06-03 |
| MaskGroup: Hierarchical Point Grouping and Masking for 3D Instance Segmentation | | 66.4 | | 43.4 | | MaskGroup | 2022-03-28 |
| Point Cloud Instance Segmentation using Probabilistic Embeddings | | 64.5 | | | | PE | 2019-11-30 |
| Learning Regional Purity for Instance Segmentation on 3D Point Clouds | ✓ Link | 64.2 | 80.6 | 42.8 | | RPGN | 2020-11-03 |
| Learning Gaussian Instance Segmentation in Point Clouds | ✓ Link | 63.8 | | | | GICN | 2020-07-20 |
| PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation | ✓ Link | 63.6 | | 40.7 | | PointGroup | 2020-04-03 |
| HIDA: Towards Holistic Indoor Understanding for the Visually Impaired via Semantic Instance Segmentation with a Wearable Solid-State LiDAR Sensor | | 63.5 | | 43.6 | | HIDA | 2021-07-07 |
| ESAM++: Efficient Online 3D Perception on the Edge | | 63.5 | | | | ESAM++ Large | 2026-05-28 |
| GroupContrast: Semantic-aware Self-supervised Representation Learning for 3D Understanding | ✓ Link | 62.3 | | | | GroupContrast | 2024-03-14 |
| Memory-based Adapters for Online 3D Scene Perception | | 60.5 | | | | TD3D-SV+Ours | 2024-03-11 |
| 3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation | ✓ Link | 59.1 | | 35.3 | 61.1 | 3D-MPA | 2020-03-30 |
| 4DContrast: Contrastive Learning with Dynamic Correspondences for 3D Scene Understanding | | 57.6 | | | | 4DContrast | 2021-12-06 |
| Spatial Semantic Embedding Network: Fast 3D Instance Segmentation with Deep Metric Learning | | 57.5 | | | | SSEN | 2020-07-07 |
| Collaborative Propagation on Multiple Instance Graphs for 3D Instance Segmentation with Single-point Supervision | ✓ Link | 56.7 | 73.9 | 34.8 | | RWSeg | 2022-08-10 |
| One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation | | 52.9 | | | | One_Thing_One_Click | 2021-04-06 |
| Learning Object Bounding Boxes for 3D Instance Segmentation on Point Clouds | ✓ Link | 48.8 | | 25.3 | 47.6 | 3D-BoNet | 2019-06-04 |
| PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things | | 47.8 | | | | PanopticFusion-inst | 2019-03-04 |
| MASC: Multi-scale Affinity with Sparse Convolution for 3D Instance Segmentation | ✓ Link | 45.9 | | | | ResNet-Backbone | 2019-02-12 |
| MASC: Multi-scale Affinity with Sparse Convolution for 3D Instance Segmentation | ✓ Link | 44.7 | | 25.4 | | MASC | 2019-02-12 |
| SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation | | 44.5 | | | | SegGroup_ins | 2020-12-18 |
| 3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans | ✓ Link | 38.2 | | | | 3D-SIS | 2018-12-17 |
| 3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation | ✓ Link | 31.9 | | | | UNet-Backbone | 2016-06-21 |
| Learning and Memorizing Representative Prototypes for 3D Point Cloud Semantic and Instance Segmentation | | 31 | | | | MPNet | 2020-01-06 |
| Serialized Point Mamba: A Serialized Point Cloud Mamba Segmentation Model | | | 76.4 | 40.0 | | Searilized Point Mamba | 2024-07-17 |
| Mask-Attention-Free Transformer for 3D Instance Segmentation | ✓ Link | | | 59.6 | | MAFT | 2023-09-04 |
| 3D-BEVIS: Bird's-Eye-View Instance Segmentation | | 24.8 | | | | 3D-BEVIS | 2019-04-03 |