Result details - ScanNet Benchmark

Submitted by ChinaUnicom -AI.

Full name	Fused 2D-3D Convolutional Neural Network
Description	This is a framework which fuses 3D segmentation results with 2D.
Input Data Types	Uses Color,Uses Geometry Uses 2D,Uses 3D
Programming language(s)	C++,PyTorch,Python
Hardware	GeForce 2080Ti 8GB,i7-8700k
Submission creation date	13 Jan, 2020
Last edited	14 Jan, 2020

Info	avg iou	bathtub	bed	bookshelf	cabinet	chair	counter	curtain	desk	door	floor	otherfurniture	picture	refrigerator	shower curtain	sink	sofa	table	toilet	wall	window
	0.636	0.825	0.820	0.179	0.648	0.463	0.549	0.742	0.676	0.628	0.961	0.420	0.379	0.684	0.381	0.732	0.723	0.599	0.827	0.851	0.634

Results for CU-Hybrid-2D Net