Submitted by Duc Tran.

Submission data

Full nameTwo-scale Superpoint with Twin-attention for 3D Instance Segmentation
Publication titleMSTA3D: Multi-scale Twin-attention for 3D Instance Segmentation
Publication authorsDuc Tran Dang Trung, Byeongkeun Kang, Yeejin Lee
Publication venueACM Multimedia 2024
Input Data TypesUses Color,Uses Geometry        Uses 3D
Programming language(s)Python
HardwareNVIDIA A100
Websitehttps://arxiv.org/abs/2411.01781
Source code or download URLhttps://github.com/vcl-seoultech/MSTA3D
Submission creation date27 Sep, 2023
Last edited5 Nov, 2024

3D semantic instance results



Infoavg apbathtubbedbookshelfcabinetchaircountercurtaindeskdoorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwindow
0.5690.7780.6750.5980.4510.7270.2800.4760.3950.4720.4570.5830.5800.7770.4620.7350.5470.9190.333