Graber, C;
Tsai, G;
Firman, M;
Brostow, G;
Schwing, A;
(2021)
Panoptic segmentation forecasting.
In:
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition.
(pp. pp. 12512-12521).
IEEE: Nashville, TN, USA.
Preview |
Text
Graber_Panoptic_Segmentation_Forecasting_CVPR_2021_paper.pdf - Accepted Version Download (6MB) | Preview |
Abstract
Our goal is to forecast the near future given a set of recent observations. We think this ability to forecast, i.e., to anticipate, is integral for the success of autonomous agents which need not only passively analyze an observation but also must react to it in real-time. Importantly, accurate forecasting hinges upon the chosen scene decomposition. We think that superior forecasting can be achieved by decomposing a dynamic scene into individual 'things' and background 'stuff'. Background 'stuff' largely moves because of camera motion, while foreground 'things' move because of both camera and individual object motion. Following this decomposition, we introduce panoptic segmentation forecasting. Panoptic segmentation forecasting opens up a middle-ground between existing extremes, which either forecast instance trajectories or predict the appearance of future image frames. To address this task we develop a two-component model: one component learns the dynamics of the background stuff by anticipating odometry, the other one anticipates the dynamics of detected things. We establish a leaderboard for this novel task, and validate a state-of-the-art model that outperforms available baselines.
| Type: | Proceedings paper |
|---|---|
| Title: | Panoptic segmentation forecasting |
| Event: | 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) |
| Dates: | 20 Jun 2021 - 25 Jun 2021 |
| ISBN-13: | 9781665445092 |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1109/CVPR46437.2021.01233 |
| Publisher version: | https://doi.org/10.1109/CVPR46437.2021.01233 |
| 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. |
| Keywords: | Image segmentation, Motion segmentation, Semantics, Dynamics, Predictive models, Cameras, Real-time systems |
| 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 Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10165507 |
Loading...
Loading...Loading...| 1. |  United States | 3 |
| 2. |  China | 3 |
| 3. |  Germany | 2 |
| 4. |  South Africa | 2 |
| 5. |  Russian Federation | 1 |
| 6. |  Australia | 1 |
| 7. |  France | 1 |
| 8. |  United Kingdom | 1 |
| 9. |  Lithuania | 1 |
| 10. |  Japan | 1 |
Archive Staff Only
 |
View Item |
