mlsanityData to 7 Oct 2026

H3DNet: 3D Object Detection Using Hybrid Geometric Primitives

arXiv 2006.05682 ↗First posted 10 Jun 2020cs.CVcited by 123

Not on the map. Why?

Abstract (arXiv)

We introduce H3DNet, which takes a colorless 3D point cloud as input and outputs a collection of oriented object bounding boxes (or BB) and their semantic labels. The critical idea of H3DNet is to predict a hybrid set of geometric primitives, i.e., BB centers, BB face centers, and BB edge centers. We show how to convert the predicted geometric primitives into object proposals by defining a distance function between an object and the geometric primitives. This distance function enables continuous optimization of object proposals, and its local minimums provide high-fidelity object proposals. H3DNet then utilizes a matching and refinement module to classify object proposals into detected objects and fine-tune the geometric parameters of the detected objects. The hybrid set of geometric primitives not only provides more accurate signals for object detection than using a single type of geometric primitives, but it also provides an overcomplete set of constraints on the resulting 3D layout. Therefore, H3DNet can tolerate outliers in predicted geometric primitives. Our model achieves state-of-the-art 3D detection results on two large datasets with real 3D scans, ScanNet and SUN RGB-D.

Key facts. Cited by 123 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 20; 2022: 34; 2023: 30; 2024: 18; 2025: 15; 2026: 6.

123 papers.

Sort:

By area:

  1. 2021ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Datacited by 442
  2. 2021An End-to-End Transformer Model for 3D Object Detectioncited by 329
  3. 2021Self-Supervised Pretraining of 3D Features on any Point-Cloudcited by 217
  4. 2021Group-Free 3D Object Detection via Transformerscited by 215
  5. 2021Neural Head Avatars from Monocular RGB Videoscited by 212
  6. 2022CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understandingcited by 198
  7. 2021ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detectioncited by 157
  8. 2022Masked Discrimination for Self-Supervised Learning on Point Cloudscited by 155
  9. 2022Multimodal Token Fusion for Vision Transformerscited by 132
  10. 2022Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipecited by 122
  11. 2023OctFormer: Octree-based Transformers for 3D Point Cloudscited by 105
  12. 2022CenterFormer: Center-based Transformer for 3D Object Detectioncited by 99
38 more
  1. 2021FCAF3D: Fully Convolutional Anchor-Free 3D Object Detectioncited by 97
  2. 2022Surface Representation for Point Cloudscited by 84
  3. 2023CLIP2: Contrastive Language-Image-Point Pretraining from Real-World Point Cloud Datacited by 69
  4. 2021Back-tracing Representative Points for Voting-based 3D Object Detection in Point Cloudscited by 67
  5. 2021Pri3D: Can 3D Priors Help 2D Representation Learning?cited by 61
  6. 2022CAGroup3D: Class-Aware Grouping for 3D Object Detection on Point Cloudscited by 58
  7. 2023PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigmcited by 56
  8. 20214DContrast: Contrastive Learning with Dynamic Correspondences for 3D Scene Understandingcited by 54
  9. 2023PiMAE: Point Cloud and Image Interactive Masked Autoencoders for 3D Object Detectioncited by 53
  10. 2021D3Net: A Unified Speaker-Listener Architecture for 3D Dense Captioning and Visual Groundingcited by 52
  11. 2023NeRF-Det: Learning Geometry-Aware Volumetric Representation for Multi-View 3D Object Detectioncited by 51
  12. 2023CoDA: Collaborative Novel Box Discovery and Cross-modal Alignment for Open-vocabulary 3D Object Detectioncited by 51
  13. 2022Ponder: Point Cloud Pre-training via Neural Renderingcited by 50
  14. 2021EPNet++: Cascade Bi-directional Fusion for Multi-Modal 3D Object Detectioncited by 49
  15. 2023Mask-Attention-Free Transformer for 3D Instance Segmentationcited by 45
  16. 2023VL-SAT: Visual-Linguistic Semantics Assisted Training for 3D Semantic Scene Graph Prediction in Point Cloudcited by 42
  17. 2022RBGNet: Ray-based Grouping for 3D Object Detectioncited by 40
  18. 2021RandomRooms: Unsupervised Pre-training from Synthetic Shapes and Randomized Layouts for 3D Object Detectioncited by 37
  19. 2021HPNet: Deep Primitive Segmentation Using Hybrid Representationscited by 35
  20. 2023V-DETR: DETR with Vertex Relative Position Encoding for 3D Object Detectioncited by 34
  21. 2023TR3D: Towards Real-Time Indoor 3D Object Detectioncited by 32
  22. 20213D Spatial Recognition without Spatially Labeled 3Dcited by 31
  23. 2021Scene Synthesis via Uncertainty-Driven Attribute Synchronizationcited by 29
  24. 2021PQ-Transformer: Jointly Parsing 3D Objects and Layouts from Point Cloudscited by 26
  25. 2023Uni3DETR: Unified 3D Detection Transformercited by 26
  26. 2022Open-Vocabulary 3D Detection via Image-level Class and Debiased Cross-modal Contrastive Learningcited by 23
  27. 2022Rotationally Equivariant 3D Object Detectioncited by 21
  28. 20223D Vision with Transformers: A Surveycited by 21
  29. 2022LCPFormer: Towards Effective 3D Point Cloud Analysis via Local Context Propagation in Transformerscited by 21
  30. 2024UniDet3D: Multi-dataset Indoor 3D Object Detectioncited by 20
  31. 2022Bridged Transformer for Vision and Point Cloud 3D Object Detectioncited by 19
  32. 2023FM-OV3D: Foundation Model-based Cross-modal Knowledge Blending for Open-Vocabulary 3D Detectioncited by 19
  33. 2024OV-Uni3DETR: Towards Unified Open-Vocabulary 3D Object Detection via Cycle-Modality Propagationcited by 19
  34. 2022RGB-Depth Fusion GAN for Indoor Depth Completioncited by 18
  35. 2022Back to Reality: Weakly-supervised 3D Object Detection with Shape-guided Label Enhancementcited by 17
  36. 2024Collaborative Novel Object Discovery and Box-Guided Cross-Modal Alignment for Open-Vocabulary 3D Object Detectioncited by 17
  37. 2023ConDaFormer: Disassembled Transformer with Local Structure Enhancement for 3D Point Cloud Understandingcited by 16
  38. 2023Mask3D: Pre-training 2D Vision Transformers by Learning Masked 3D Priorscited by 15

50 most cited of 123 All 123 (JSON)