Submitted by Chen Liu.

Submission data

Full name	MASC: Multi-scale Affinity with Sparse Convolution for 3D Instance Segmentation
Description	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. A simple yet effective clustering algorithm segments points into instances based on the predicted affinity and the mesh topology. The semantic for each instance is determined by the semantic prediction. Experiments show that our method outperforms the state-of-theart instance segmentation methods by a large margin on the widely used ScanNet benchmark [2]. We share our code publicly at https://github.com/art-programmer/MASC.
Publication title	MASC: Multi-scale Affinity with Sparse Convolution for 3D Instance Segmentation
Publication authors	Chen Liu, Yasutaka Furukawa
Publication URL	https://arxiv.org/abs/1902.04478
Input Data Types	Uses Color,Uses Geometry        Uses 3D
Programming language(s)	PyTorch
Hardware	TitanX
Website	https://github.com/art-programmer/MASC/blob/master/README.md
Source code or download URL	https://github.com/art-programmer/MASC/blob/master/README.md
Submission creation date	17 Jan, 2019
Last edited	13 Feb, 2019

3D semantic instance results