Submitted by Yingqi Wang.

Submission data

Full nameDynamic Graph CNN
DescriptionAn implementation of DGCNN on the ScanNet dataset
Publication titleDynamic Graph CNN for Learning on Point Clouds
Publication authorsYue Wang, Yongbin Sun, Ziwei Liu, Sanjay E. Sarma, Michael M. Bronstein, Justin M. Solomon
Publication venueTOG 2019
Publication URLhttps://arxiv.org/abs/1801.07829
Input Data TypesUses Color        Uses 3D
Programming language(s)Python(PyTorch) with CUDA extensions
HardwareGeforce RTX2080
Source code or download URLhttps://github.com/AnTao97/dgcnn.pytorch
Submission creation date14 Jul, 2022
Last edited21 Jul, 2022

3D semantic label results

Infoavg ioubathtubbedbookshelfcabinetchaircountercurtaindeskdoorfloorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwallwindow
copyleft0.4460.4740.6230.4630.3660.6510.3100.3890.3490.3300.9370.2710.1260.2850.2240.3500.5770.4450.6250.7230.394