Gomes, P;
Rossi, S;
Toni, L;
(2021)
Spatio-temporal Graph-RNN for Point Cloud Prediction.
In:
2021 IEEE International Conference on Image Processing (ICIP).
IEEE: Anchorage, AK, USA.
Preview |
Text
2102.07482v3.pdf - Accepted Version Download (6MB) | Preview |
Abstract
In this paper, we propose an end-to-end learning network to predict future frames in a point cloud sequence. As main novelty, an initial layer learns topological information of point clouds as geometric features, to form representative spatio-temporal neighborhoods. This module is followed by multiple Graph-RNN cells. Each cell learns points dynamics (i.e., RNN states) by processing each point jointly with the spatio-temporal neighbouring points. We tested the network performance with a MINST dataset of moving digits, a synthetic human bodies motions and JPEG dynamic bodies datasets. Simulation results demonstrate that our method outperforms baseline ones that neglect geometry features information.
| Type: | Proceedings paper |
|---|---|
| Title: | Spatio-temporal Graph-RNN for Point Cloud Prediction |
| Event: | 2021 IEEE International Conference on Image Processing (ICIP) |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1109/ICIP42928.2021.9506084 |
| Publisher version: | https://doi.org/10.1109/ICIP42928.2021.9506084 |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Electronic and Electrical Eng |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10128889 |
Archive Staff Only
 |
View Item |
