Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

H3DNet: 3D Object Detection Using Hybrid Geometric Primitives

About

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.

Zaiwei Zhang, Bo Sun, Haitao Yang, Qixing Huang• 2020

Related benchmarks

TaskDatasetResultRank
3D Object DetectionScanNet V2 (val)
mAP@0.2567.2
352
3D Object DetectionSUN RGB-D (val)
mAP@0.2560.1
158
3D Object DetectionScanNet
mAP@0.2567.2
123
3D Object DetectionSUN RGB-D
mAP@0.2560.11
104
3D Object DetectionSUN RGB-D v1 (val)
mAP@0.2560.1
81
3D Object DetectionScanNet (val)
mAP@0.2567.2
66
3D Object DetectionSUN RGB-D (test)
mAP@0.2561.6
64
3D Object DetectionScanNet V2
AP5048.1
54
Object DetectionScanNet V2 (val)--
33
Indoor Object DetectionSUN RGB-D (test)
mAP@0.539
19
Showing 10 of 13 rows

Other info

Code

Follow for update