Submitted by chaolong yang.

Submission data

Full nameDeep Multi-view Fusion Network
Description2D-3D feature fusion
Publication titleTowards Deeper and Better Multi-view Feature Fusion for 3D Semantic Segmentation
Publication authorsC.Yang, Y.Yan, W.Zhao, J.Ye, X.Yang, A.Hussain, B.Dong, K.Huang
Publication venueICONIP 2023
Publication URLhttps://arxiv.org/abs/2212.06682
Input Data TypesUses Color,Uses Geometry        Uses 2D,Uses 3D
Programming language(s)python, C++ with CUDA
HardwareQuadro RTX8000
Submission creation date21 Oct, 2021
Last edited1 Aug, 2023

3D semantic label results

Infoavg ioubathtubbedbookshelfcabinetchaircountercurtaindeskdoorfloorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwallwindow
0.7520.9060.7930.8020.6890.8250.5560.8670.6810.6020.9600.5550.3650.7790.8590.7470.7950.7170.9170.8560.764