Space-Time Co-Segmentation of Articulated Point Cloud Sequences
| dc.contributor.author | Yuan, Qing | en_US |
| dc.contributor.author | Li, Guiqing | en_US |
| dc.contributor.author | Xu, Kai | en_US |
| dc.contributor.author | Chen, Xudong | en_US |
| dc.contributor.author | Huang, Hui | en_US |
| dc.contributor.editor | Joaquim Jorge and Ming Lin | en_US |
| dc.date.accessioned | 2016-04-26T08:38:49Z | |
| dc.date.available | 2016-04-26T08:38:49Z | |
| dc.date.issued | 2016 | en_US |
| dc.description.abstract | Consistent segmentation is to the center of many applications based on dynamic geometric data. Directly segmenting a raw 3D point cloud sequence is a challenging task due to the low data quality and large inter-frame variation across the whole sequence. We propose a local-to-global approach to co-segment point cloud sequences of articulated objects into near-rigid moving parts. Our method starts from a per-frame point clustering, derived from a robust voting-based trajectory analysis. The local segments are then progressively propagated to the neighboring frames with a cut propagation operation, and further merged through all frames using a novel space-time segment grouping technqiue, leading to a globally consistent and compact segmentation of the entire articulated point cloud sequence. Such progressive propagating and merging, in both space and time dimensions, makes our co-segmentation algorithm especially robust in handling noise, occlusions and pose/view variations that are usually associated with raw scan data. | en_US |
| dc.description.number | 2 | en_US |
| dc.description.sectionheaders | Geometric Modeling | en_US |
| dc.description.seriesinformation | Computer Graphics Forum | en_US |
| dc.description.volume | 35 | en_US |
| dc.identifier.doi | 10.1111/cgf.12843 | en_US |
| dc.identifier.issn | 1467-8659 | en_US |
| dc.identifier.pages | 419-429 | en_US |
| dc.identifier.uri | https://doi.org/10.1111/cgf.12843 | en_US |
| dc.publisher | The Eurographics Association and John Wiley & Sons Ltd. | en_US |
| dc.subject | I.3.5 [Computer Graphics] | en_US |
| dc.subject | Computational Geometry and Object Modeling | en_US |
| dc.subject | Modeling | en_US |
| dc.subject | I.3.7 [Computer Graphics] | en_US |
| dc.subject | Three Dimensional Graphics and Realism | en_US |
| dc.subject | Animation | en_US |
| dc.title | Space-Time Co-Segmentation of Articulated Point Cloud Sequences | en_US |