| State Space Model Meets Transformer: A New Paradigm for 3D Object Detection | ✓ Link | 67.9 | 78.8 | DEST (based on V-DETR) (TTA) | 2025-03-18 |
| Relation3D: Enhancing Relation Modeling for Point Cloud Instance Segmentation | ✓ Link | 66.7 | 75.3 | Relation3D | 2025-06-22 |
| UniDet3D: Multi-dataset Indoor 3D Object Detection | ✓ Link | 66.1 | 77.5 | UniDet3D | 2024-09-06 |
| V-DETR: DETR with Vertex Relative Position Encoding for 3D Object Detection | ✓ Link | 65.9 | 77.8 | V-DETR | 2023-08-08 |
| MV-DETR: Multi-modality indoor object detection by Multi-View DEtecton TRansformers | | 65.8 | 78.0 | UDeerMvDETR | 2024-08-13 |
| UniGeo: A Unified 3D Indoor Object Detection Framework Integrating Geometry-Aware Learning and Dynamic Channel Gating | | 65.6 | 77.7 | UniGeo | 2026-01-30 |
| OneFormer3D: One Transformer for Unified Point Cloud Segmentation | ✓ Link | 65.3 | 76.9 | OneFormer3D | 2023-11-24 |
| | 65.3 | 74.6 | BFL | |
| H^2A^2: Homogeneity-Aware and Heterogeneity-Aware Feature Perception for Unified Indoor 3D Object Detection | | 63.8 | 77.5 | H2A2 | 2026-06-03 |
| Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding | ✓ Link | 63.2 | 76.4 | Swin3D-L+CAGroup3D | 2023-04-14 |
| Query Refinement Transformer for 3D Instance Segmentation | | 61.7 | 73.4 | QueryFormer | 2023-01-01 |
| CAGroup3D: Class-Aware Grouping for 3D Object Detection on Point Clouds | ✓ Link | 61.3 | 75.1 | CAGroup3D | 2022-10-09 |
| GraphFusion3D: Dynamic Graph Attention Convolution with Adaptive Cross-Modal Transformer for 3D Object Detection | | 60.8 | 75.1 | GraphFusion3D (P+I) | 2025-12-02 |
| TUN3D: Towards Real-World Scene Understanding from Unposed Images | ✓ Link | 60.2 | 72.7 | TUN3D (GT point clouds) (extra data) | 2025-09-23 |
| Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise Binarization | ✓ Link | 60.1 | 69.3 | PBNet | 2022-07-22 |
| Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast | ✓ Link | 59.6 | 73.1 | Point-GCC+TR3D | 2023-05-31 |
| SPGroup3D: Superpoint Grouping Network for Indoor 3D Object Detection | ✓ Link | 59.6 | 74.3 | SPGroup3D | 2023-12-21 |
| SoftGroup for 3D Instance Segmentation on Point Clouds | ✓ Link | 59.4 | 71.6 | SoftGroup | 2022-03-03 |
| TR3D: Towards Real-Time Indoor 3D Object Detection | | 59.3 | 72.9 | TR3D | 2023-02-06 |
| State Space Model Meets Transformer: A New Paradigm for 3D Object Detection | ✓ Link | 58.1 | 71.3 | DEST (based on GroupFree3D) | 2025-03-18 |
| GraphFusion3D: Dynamic Graph Attention Convolution with Adaptive Cross-Modal Transformer for 3D Object Detection | | 57.9 | 72.8 | GraphFusion3D (P) | 2025-12-02 |
| FCAF3D: Fully Convolutional Anchor-Free 3D Object Detection | ✓ Link | 57.3 | 71.5 | FCAF3D | 2021-12-01 |
| DQS3D: Densely-matched Quantization-aware Semi-supervised 3D Detection | ✓ Link | 56.3 | 71.9 | DQS3D (100% labels) | 2023-04-25 |
| RBGNet: Ray-based Grouping for 3D Object Detection | ✓ Link | 55.2 | 70.6 | RBGNet | 2022-04-05 |
| Surface Representation for Point Clouds | ✓ Link | 54.8 | 71.2 | RepSurf-U | 2022-05-11 |
| Multimodal Token Fusion for Vision Transformers | ✓ Link | 54.2 | 70.8 | TokenFusion | 2022-04-19 |
| Group-Free 3D Object Detection via Transformers | ✓ Link | 52.8 | 69.1 | GroupFree3D | 2021-04-01 |
| Back-tracing Representative Points for Voting-based 3D Object Detection in Point Clouds | ✓ Link | 50.9 | 66.1 | BRNet | 2021-04-13 |
| Memory-based Adapters for Online 3D Scene Perception | | 49.9 | | FCAF3D-SV+Ours | 2024-03-11 |
| 3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation | ✓ Link | 49.2 | 64.2 | 3D-MPA | 2020-03-30 |
| H3DNet: 3D Object Detection Using Hybrid Geometric Primitives | ✓ Link | 48.1 | 67.2 | H3DNet | 2020-06-10 |
| An End-to-End Transformer Model for 3D Object Detection | ✓ Link | 47.0 | 65.0 | 3DETR-m | 2021-09-16 |
| Gaussian2Scene: 3D Scene Representation Learning via Self-supervised Learning with 3D Gaussian Splatting | | 43.3 | 62.9 | Gaussian2Scene + 3DETR (extra data) | 2025-06-10 |
| GroupContrast: Semantic-aware Self-supervised Representation Learning for 3D Understanding | ✓ Link | 41.1 | | GroupContrast | 2024-03-14 |
| Point Cloud Pre-Training With Natural 3D Structures | ✓ Link | 39.9 | 63.4 | VoteNet (PC-FractalDB) | 2022-01-01 |
| 3DGS-DET: Empower 3D Gaussian Splatting with Boundary Guidance and Box-Focused Sampling for 3D Object Detection | ✓ Link | 37.8 | 59.9 | 3DGS-DET (extra data) | 2024-10-02 |
| Boosting Multi-View Indoor 3D Object Detection via Adaptive 3D Volume Construction | ✓ Link | 37.1 | 62.2 | SGCDet (depth supervision) (extra data) | 2025-07-24 |
| Generative Sparse Detection Networks for 3D Single-shot Object Detection | ✓ Link | 34.8 | 62.8 | GSDN | 2020-06-22 |
| A Hierarchical Graph Network for 3D Object Detection on Point Clouds | | 34.4 | 61.3 | HGNet | 2020-06-01 |
| GO-N3RDet: Geometry Optimized NeRF-enhanced 3D Object Detector | ✓ Link | 33.7 | 58.6 | GO-N3RDet-R101* | 2025-03-19 |
| Deep Hough Voting for 3D Object Detection in Point Clouds | ✓ Link | 33.5 | 58.6 | VoteNet | 2019-04-21 |
| NeRF-Det: Learning Geometry-Aware Volumetric Representation for Multi-View 3D Object Detection | ✓ Link | 29.8 | | NeRF-Det R101-2x (low-res, depth supervision) (extra data) | 2023-07-27 |
| ImGeoNet: Image-induced Geometry-aware Voxel Representation for Multi-view 3D Object Detection | ✓ Link | 28.4 | 54.8 | ImGeoNet (RGB only) | 2023-08-17 |
| ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detection | ✓ Link | 22.7 | 48.1 | ImVoxelNet (RGB only) | 2021-06-02 |
| 3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans | ✓ Link | 22.5 | 40.2 | 3D-SIS | 2018-12-17 |
| GSPN: Generative Shape Proposal Network for 3D Instance Segmentation in Point Cloud | ✓ Link | 17.7 | 30.6 | GSPN | 2018-12-08 |
| SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation | ✓ Link | | 20.7 | SGPN | 2017-11-23 |
| NeRF-Det: Learning Geometry-Aware Volumetric Representation for Multi-View 3D Object Detection | ✓ Link | | 53.3 | NeRF-Det R101-2x (high-res, depth supervision) (extra data) | 2023-07-27 |