Submitted by kangcheng Liu.

Submission data

Full nameWS3D_LR_Ins
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 date23 Aug, 2021
Last edited2 Aug, 2023

3D semantic instance results with limited reconstructions



Infoavg ap 25%bathtubbedbookshelfcabinetchaircountercurtaindeskdoorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwindow
0.7261.0000.7970.7300.6690.8510.4100.7650.6930.5280.5830.3880.6381.0000.8800.8740.6530.9750.631