Submitted by kangcheng Liu.

Submission data

Full nameWS3D_LA_OD
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)C++
HardwareCore i5 CPU, A Single GTX 1080Ti GPU
Submission creation date26 Aug, 2021
Last edited2 Aug, 2023

3D object detection results with limited annotations



Infoavg ap 25%bathtubbedbookshelfcabinetchaircountercurtaindeskdoorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwindow
permissive0.5430.9170.8750.7360.2970.8440.4030.2320.5270.4750.4270.1370.4510.2800.4540.8720.4960.9090.435