Submitted anonymously.

Submission data

Full nameROSMRF: Real-time Online 3D Semantic segmentation for mobile scene
DescriptionA novel multi-modal fusion framework, named ROSMRF, to online achieve semantic segmentation of 3D scenes.
Input Data TypesUses Color,Uses Geometry        Uses 2D
Programming language(s)python with cuda
HardwareTITAN RTX
Submission creation date28 Dec, 2020
Last edited10 Mar, 2021

3D semantic label results

Infoavg ioubathtubbedbookshelfcabinetchaircountercurtaindeskdoorfloorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwallwindow
0.6730.7890.7480.7630.6350.8140.4070.7470.5810.5730.9500.4840.2710.6070.7540.6490.7740.5960.8830.8230.606