Submitted anonymously.

Submission data

Full nameStratified Transformer for 3D Point Cloud Segmentation
DescriptionStratified Transformer adopts a novel stratified sampling strategy, and develops the point embedding module as well as the contextual position encoding to further boost the performance.
Input Data TypesUses Color        Uses 3D
Programming language(s)Python with CUDA
HardwareTesla V100
Submission creation date31 Aug, 2021
Last edited1 Dec, 2021

3D semantic label results

Infoavg ioubathtubbedbookshelfcabinetchaircountercurtaindeskdoorfloorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwallwindow
0.7470.9010.8030.8450.7570.8460.5120.8250.6960.6450.9560.5760.2620.7440.8610.7420.7700.7050.8990.8600.734