Submitted by Ji Hou.

Submission data

Full name3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans
Publication title3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans
Publication authorsJi Hou, Angela Dai, Matthias Niessner
Publication venueCVPR 2019
Publication URLhttps://arxiv.org/abs/1812.07003
Input Data TypesUses Color,Uses Geometry        Uses 2D,Uses 3D
Programming language(s)PyTorch
HardwareGTX1080Ti
Source code or download URLhttps://github.com/Sekunde/3D-SIS
Submission creation date23 Nov, 2018
Last edited27 Apr, 2019

3D semantic instance results



Infoavg ap 25%bathtubbedbookshelfcabinetchaircountercurtaindeskdoorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwindow
permissive0.5581.0000.7730.6140.5030.6910.2000.4120.4980.5460.3110.1030.6000.8570.3820.7990.4450.9380.371