H3DNet: 3D Object Detection Using Hybrid Geometric Primitives

10 Jun 2020Zaiwei ZhangBo SunHaitao YangQixing 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... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
3D Object Detection ScanNetV2 H3DNet [email protected] 67.2 # 1
[email protected] 48.1 # 2
3D Object Detection SUN-RGBD val H3DNet MAP 60.1 # 2

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet