3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans

CVPR 2019 Ji HouAngela DaiMatthias Nießner

We introduce 3D-SIS, a novel neural network architecture for 3D semantic instance segmentation in commodity RGB-D scans. The core idea of our method is to jointly learn from both geometric and color signal, thus enabling accurate instance predictions... (read more)

PDF Abstract

Evaluation results from the paper


Task Dataset Model Metric name Metric value Global rank Compare
3D Semantic Instance Segmentation ScanNetV2 3D-SIS [email protected] 36.2 # 1