Submitted by Abhijit Kundu.

Submission data

Full nameVirtual Multi-view Fusion for 3D Semantic Segmentation
Description2D projection (rendering) of labels obtained by output of 3D virtual multi-view fusion. See paper for details.
Publication titleVirtual Multi-view Fusion for 3D Semantic Segmentation
Publication authorsAbhijit Kundu, Xiaoqi Yin, Alireza Fathi, David Ross, Brian Brewington, Thomas Funkhouser, Caroline Pantofaru
Publication venueECCV 2020
Publication URLhttps://arxiv.org/abs/2007.13138
Input Data TypesUses Color,Uses Geometry        Uses 2D,Uses 3D
Programming language(s)Python, C++, TensorFlow
HardwareNVidia V100
Websitehttps://abhijitkundu.info/projects/multiview_segmentation/
Submission creation date20 Feb, 2016
Last edited13 Aug, 2020

2D semantic label results

Infoavg ioubathtubbedbookshelfcabinetchaircountercurtaindeskdoorfloorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwallwindow
0.7450.8610.8390.8810.6720.5120.4220.8980.7230.7140.9540.4540.5090.7730.8950.7560.8200.6530.9350.8910.728