Submitted by Julian Chibane.

Submission data

Full nameBox2Mask weakly supervised by bounding boxes
DescriptionBox2Mask is trained only using bounding box supervision - no per-point labels are needed.
Publication titleBox2Mask: Weakly Supervised 3D Semantic Instance Segmentation Using Bounding Boxes
Publication authorsJulian Chibane, Francis Engelmann, Tuan Anh Tran, Gerard Pons-Moll
Publication venueECCV 2022
Publication URLhttp://virtualhumans.mpi-inf.mpg.de/papers/chibane22Box2Mask/Chibane_Box2Mask.pdf
Input Data TypesUses Color        Uses 3D
Programming language(s)Python, Pytorch
HardwareNVIDIA Quadro RTX 8000
Websitehttps://virtualhumans.mpi-inf.mpg.de/box2mask/
Submission creation date5 Mar, 2022
Last edited7 Jul, 2022

3D semantic instance results with limited annotations



Infoavg apbathtubbedbookshelfcabinetchaircountercurtaindeskdoorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwindow
0.3270.8520.3360.3810.1620.5080.0520.2050.0610.1540.3130.2080.2990.5300.1650.4920.2130.7840.162