Submitted by QI Xiaojuan.

Submission data

Full nameOne Thing One Click
Publication titleOne Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation
Publication authorsZhengzhe Liu, Xiaojuan Qi, Chi-Wing Fu
Publication venueCVPR 2021
Publication URLhttps://arxiv.org/abs/2104.02246
Input Data TypesUses Color,Uses Geometry        Uses 3D
Programming language(s)python
Hardware2080 ti
Submission creation date26 Mar, 2021
Last edited29 Aug, 2021

3D semantic label results

Infoavg ioubathtubbedbookshelfcabinetchaircountercurtaindeskdoorfloorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwallwindow
0.6930.7430.7940.6550.6840.8220.4970.7190.6220.6170.9770.4470.3390.7500.6640.7030.7900.5960.9460.8550.647