MASC: Multi-scale Affinity with Sparse Convolution for 3D Instance Segmentation

12 Feb 2019 Chen Liu Yasutaka Furukawa

We propose a new approach for 3D instance segmentation based on sparse convolution and point affinity prediction, which indicates the likelihood of two points belonging to the same instance. The proposed network, built upon submanifold sparse convolution [3], processes a voxelized point cloud and predicts semantic scores for each occupied voxel as well as the affinity between neighboring voxels at different scales... (read more)

PDF Abstract

Datasets


Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
3D Instance Segmentation ScanNet MASC mAP 0.447 # 1
3D Instance Segmentation ScanNet(v2) MASC Mean AP @ 0.5 44.7 # 7
mAP 25.4 # 4

Methods used in the Paper


METHOD TYPE
Convolution
Convolutions