Papers › H3DNet: 3D Object Detection Using Hybrid Geometric Primitives
H3DNet: 3D Object Detection Using Hybrid Geometric Primitives
Zaiwei Zhang, Bo Sun, Haitao Yang, Qi-Xing Huang
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.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 3D Object Detection | ARKitScenes | H3DNet | mAP@0.25 | 38.3 | #3 of 4 | Archive leaderboard | report |
| 3D Object Detection | SUN-RGBD val | H3DNet | mAP@0.25 | 60.1 | #21 of 32 | Archive leaderboard | report |
| 3D Object Detection | SUN-RGBD val | H3DNet | mAP@0.5 | 39.0 | #21 of 32 | Archive leaderboard | report |
| 3D Object Detection | ScanNetV2 | H3DNet | mAP@0.25 | 67.2 | #23 of 33 | Archive leaderboard | report |
| 3D Object Detection | ScanNetV2 | H3DNet | mAP@0.5 | 48.1 | #23 of 33 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections