Group-Free 3D Object Detection via Transformers

1 Apr 2021 Ze Liu Zheng Zhang Yue Cao Han Hu Xin Tong

Recently, directly detecting 3D objects from 3D point clouds has received increasing attention. To extract object representation from an irregular point cloud, existing methods usually take a point grouping step to assign the points to an object candidate so that a PointNet-like network could be used to derive object features from the grouped points... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
3D Object Detection ScanNetV2 GroupFree3D mAP@0.25 69.1 # 1
mAP@0.5 52.8 # 1
3D Object Detection SUN-RGBD GroupFree3D mAP@0.25 63.0 # 2
mAP@0.5 45.2 # 1
3D Object Detection SUN-RGBD val GroupFree3D(Geo only) mAP@0.25 63.0 # 1
mAP@0.5 45.2 # 1

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