Submitted by Liyii Luo.

Submission data

Full nameWeakly Supervised 3D Scene Parsing with Viewpoint Bottleneck
Publication titlePointly-supervised 3D Scene Parsing with Viewpoint Bottleneck
Publication authorsLiyi Luo, Beiwen Tian, Hao Zhao, Guyue Zhou
Publication URLhttps://arxiv.org/abs/2109.08553
Input Data TypesUses Color,Uses Geometry        Uses 3D
Programming language(s)python with CUDA
HardwareGeForce RTX 3090
Source code or download URLhttps://github.com/OPEN-AIR-SUN/Viewpoint-Bottleneck
Submission creation date4 Jun, 2021
Last edited20 Sep, 2021

3D semantic label results with limited annotations



Infoavg ioubathtubbedbookshelfcabinetchaircountercurtaindeskdoorfloorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwallwindow
0.6500.7780.7310.6880.6170.8120.4460.7390.6180.5400.9450.4150.2040.6230.6760.5940.7440.5760.8680.8110.582