Submitted by Beiwen Tian.

Submission data

Full nameViewpoint Bottleneck and Uncertainty-Spectrum Modeling
Publication titleVIBUS: Data-efficient 3D Scene Parsing with VIewpoint Bottleneck and Uncertainty-Spectrum Modeling
Publication authorsBeiwen Tian,Liyi Luo,Hao Zhao,Guyue Zhou
Publication venueISPRS Journal of Photogrammetry and Remote Sensing
Publication URLhttps://arxiv.org/abs/2210.11472
Input Data TypesUses Color        Uses 3D
Programming language(s)Python with CUDA
HardwareAMD 7742, NVIDIA A100, 128GB RAM
Source code or download URLhttps://github.com/AIR-DISCOVER/VIBUS
Submission creation date10 Jan, 2022
Last edited21 Oct, 2022

3D semantic label results with limited annotations



Infoavg ioubathtubbedbookshelfcabinetchaircountercurtaindeskdoorfloorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwallwindow
permissive0.6910.8600.7310.7380.6720.8600.4700.7660.6250.5470.9490.4910.2550.6930.7150.7120.7780.5970.9110.8160.635