3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation

30 Mar 2020 β€’ Francis Engelmann β€’ Martin Bokeloh β€’ Alireza Fathi β€’ Bastian Leibe β€’ Matthias Nießner

We present 3D-MPA, a method for instance segmentation on 3D point clouds. Given an input point cloud, we propose an object-centric approach where each point votes for its object center... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
3D Instance Segmentation S3DIS 3D-MPA mRec 64.1 # 2
mPrec 66.7 # 4
3D Instance Segmentation ScanNet(v2) 3D-MPA mRec 61.1 # 1
Mean AP @ 0.5 59.1 # 3
mAP 35.3 # 3
3D Object Detection ScanNetV2 3D-MPA [email protected] 64.2 # 2
[email protected] 49.2 # 1
3D Semantic Instance Segmentation ScanNetV2 3D-MPA [email protected] 61.1 # 1

Methods used in the Paper


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