| Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast | ✓ Link | 69.7 | 54.0 | | Point-GCC+TR3D+FF | 2023-05-31 |
| TR3D: Towards Real-Time Indoor 3D Object Detection | | 69.4 | 53.4 | | TR3D+FF | 2023-02-06 |
| State Space Model Meets Transformer: A New Paradigm for 3D Object Detection | ✓ Link | 69.2 | 52.2 | | DEST (based on V-DETR) (TTA) | 2025-03-18 |
| V-DETR: DETR with Vertex Relative Position Encoding for 3D Object Detection | ✓ Link | 68.0 | 51.1 | | V-DETR | 2023-08-08 |
| Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast | ✓ Link | 67.7 | 51.0 | | Point-GCC+TR3D | 2023-05-31 |
| Boosting 3D Object Detection via Object-Focused Image Fusion | ✓ Link | 67.4 | 51.2 | | DeMF | 2022-07-21 |
| TR3D: Towards Real-Time Indoor 3D Object Detection | | 67.1 | 50.4 | | TR3D (Geo only) | 2023-02-06 |
| CAGroup3D: Class-Aware Grouping for 3D Object Detection on Point Clouds | ✓ Link | 66.8 | 50.2 | | CAGroup3D(Geo only) | 2022-10-09 |
| OctFormer: Octree-based Transformers for 3D Point Clouds | ✓ Link | 66.2 | 50.6 | | OctFormer | 2023-05-04 |
| SPGroup3D: Superpoint Grouping Network for Indoor 3D Object Detection | ✓ Link | 65.4 | 47.1 | | SPGroup3D(Geo only) | 2023-12-21 |
| State Space Model Meets Transformer: A New Paradigm for 3D Object Detection | ✓ Link | 65.3 | 48.4 | | DEST (based on GroupFree3D) | 2025-03-18 |
| Multimodal Token Fusion for Vision Transformers | ✓ Link | 64.9 | 48.3 | | TokenFusion | 2022-04-19 |
| Surface Representation for Point Clouds | ✓ Link | 64.9 | 47.7 | | RepSurf-U | 2022-05-11 |
| FCAF3D: Fully Convolutional Anchor-Free 3D Object Detection | ✓ Link | 64.2 | 48.9 | | FCAF3D (Geo only) | 2021-12-01 |
| RBGNet: Ray-based Grouping for 3D Object Detection | ✓ Link | 64.1 | 47.2 | | RBGNet(Geo only) | 2022-04-05 |
| LCPFormer: Towards Effective 3D Point Cloud Analysis via Local Context Propagation in Transformers | ✓ Link | 63.2 | 46.2 | | LCPFormer | 2022-10-23 |
| Group-Free 3D Object Detection via Transformers | ✓ Link | 63.0 | 45.2 | | GroupFree3D(Geo only) | 2021-04-01 |
| A Hierarchical Graph Network for 3D Object Detection on Point Clouds | | 61.6 | | | HGNet (Geo only) | 2020-06-01 |
| Back-tracing Representative Points for Voting-based 3D Object Detection in Point Clouds | ✓ Link | 61.1 | 43.7 | | BRNet(Geo only) | 2021-04-13 |
| Point Cloud Pre-Training With Natural 3D Structures | ✓ Link | 60.2 | 35.2 | | VoteNet (PC-FractalDB) | 2022-01-01 |
| H3DNet: 3D Object Detection Using Hybrid Geometric Primitives | ✓ Link | 60.1 | 39.0 | | H3DNet | 2020-06-10 |
| Deep Hough Voting for 3D Object Detection in Point Clouds | ✓ Link | 59.1 | 35.8 | | VoteNet (Geo only) | 2019-04-21 |
| An End-to-End Transformer Model for 3D Object Detection | ✓ Link | 59.1 | 32.7 | | 3DETR-m | 2021-09-16 |
| Clouds of Oriented Gradients for 3D Detection of Objects, Surfaces, and Indoor Scene Layouts | | 54.3 | | | COG+surface+context | 2019-06-11 |
| Frustum PointNets for 3D Object Detection from RGB-D Data | ✓ Link | 54.0 | | 0.12 | F-PointNet | 2017-11-22 |
| 3D Object Detection With Latent Support Surfaces | | 51.0 | | | COG+surface | 2018-06-01 |
| Three-Dimensional Object Detection and Layout Prediction Using Clouds of Oriented Gradients | | 47.6 | | | COG | 2016-06-01 |
| 2D-Driven 3D Object Detection in RGB-D Images | | 45.1 | | 4.15 | 2D-driven | 2017-10-01 |
| 3D Object Detection and Instance Segmentation from 3D Range and 2D Color Images | | 45.0 | | 0.24 | Frustum VoxNet v2 (FPN + 3D ResNetFCN6 V2) | 2021-02-09 |
| Frustum VoxNet for 3D object detection from RGB-D or Depth images | | 37.7 | | 0.16 | Frustum VoxNet (+3D ResNetFCN6) | 2019-10-12 |
| Frustum VoxNet for 3D object detection from RGB-D or Depth images | | | | 0.048 | Frustum VoxNet (YOLO v3+3D ResNetFCN6) | 2019-10-12 |
| Deep Sliding Shapes for Amodal 3D Object Detection in RGB-D Images | | | | 19.55 | DSS | 2015-11-07 |