3 Hits in 3.5 sec

Rescan: Inductive Instance Segmentation for Indoor RGBD Scans [article]

Maciej Halber and Yifei Shi and Kai Xu and Thomas Funkhouser
2019 arXiv   pre-print
Our algorithm operates inductively by using the temporal model resulting from past observations to infer an instance segmentation of a new scan, which is then used to update the temporal model.  ...  During experiments with a new benchmark for the new task, our algorithm outperforms alternate approaches based on state-of-the-art networks for semantic instance segmentation.  ...  Chang and Manolis Savva for insightful discussions. We also thank Graham et al. [21] and Liu et al. [33] for the comparison codes, and Dai et al. for the ScanNet data [10] .  ... 
arXiv:1909.11268v1 fatcat:peg7makkunbhdkschsv5xwqvni

MultiBodySync: Multi-Body Segmentation and Motion Estimation via 3D Scan Synchronization [article]

Jiahui Huang, He Wang, Tolga Birdal, Minhyuk Sung, Federica Arrigoni, Shi-Min Hu, Leonidas Guibas
2021 arXiv   pre-print
We present MultiBodySync, a novel, end-to-end trainable multi-body motion segmentation and rigid registration framework for multiple input 3D point clouds.  ...  The two non-trivial challenges posed by this multi-scan multibody setting that we investigate are: (i) guaranteeing correspondence and segmentation consistency across multiple input point clouds capturing  ...  Rescan: Inductive instance segmentation for indoor rgbd scans.  ... 
arXiv:2101.06605v3 fatcat:mci7c5iuwzggpechfp3rfv42qa

Table of Contents

2019 2019 IEEE/CVF International Conference on Computer Vision (ICCV)  
: Inductive Instance Segmentation for Indoor RGBD Scans 2541 Maciej Halber (Princeton University), Yifei Shi (National University of Defense Technology), Kai Xu (National University of Defense Technology  ...  Hong Kong) Segmentation, Grouping, & Shape Explicit Shape Encoding for Real-Time Instance Segmentation 5167 Wenqiang Xu (Shanghai Jiaotong University), Haiyang Wang (SHANG HAI JIAO TONG UNIVERSITY  ... 
doi:10.1109/iccv.2019.00004 fatcat:5aouo4scprc75c7zetsimylj2y