Submitted by kangcheng Liu.

Submission data

Full nameWS3D_LA_Sem
DescriptionData-Efficient 3D Scene Understanding
Publication titleWS3D: Weakly Supervised 3D Scene Segmentation with Region-Level Boundary Awareness and Instance Discrimination
Publication authorsKangcheng Liu
Publication venueEuropean Conference on Computer Vision (ECCV), 2022
Publication URLhttps://link.springer.com/chapter/10.1007/978-3-031-19815-1_3
Input Data TypesUses Geometry        Uses 3D
Programming language(s)Python
HardwareCore i5 CPU, A Single GTX 1080Ti GPU
Submission creation date19 Aug, 2021
Last edited2 Aug, 2023

3D semantic label results with limited annotations



Infoavg ioubathtubbedbookshelfcabinetchaircountercurtaindeskdoorfloorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwallwindow
permissive0.6940.8950.7430.7670.6750.8260.4960.8170.6120.6130.9470.4600.2540.5580.8110.7100.7760.6160.8740.8220.603