Jeong, H;
Huang, CHP;
Chul Ye, J;
Mitra, NJ;
Ceylan, D;
(2025)
Track4Gen: Teaching Video Diffusion Models to Track Points Improves Video Generation.
In:
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition.
(pp. pp. 7276-7287).
IEEE
Preview |
Text
Mitra_Teaching Video Diffusion Models to Track Points Improves Video Generation_AAM.pdf Download (5MB) | Preview |
Abstract
While recent foundational video generators produce visually rich output, they still struggle with appearance drift, where objects gradually degrade or change inconsistently across frames, breaking visual coherence. We hypothesize that this is because there is no explicit supervision in terms of spatial tracking at the feature level. We propose Track4Gen, a spatially aware video generator that combines video diffusion loss with point tracking across frames, providing enhanced spatial supervision on the diffusion features. Track4Gen merges the video generation and point tracking tasks into a single network by making minimal changes to existing video generation architectures. Using Stable Video Diffusion [4] as a backbone, Track4Gen demonstrates that it is possible to unify video generation and point tracking, which are typically handled as separate tasks. Our extensive evaluations show that Track4Gen effectively reduces appearance drift, resulting in temporally stable and visually coherent video generation. Project page: hyeonho99.github.io/track4gen
| Type: | Proceedings paper |
|---|---|
| Title: | Track4Gen: Teaching Video Diffusion Models to Track Points Improves Video Generation |
| Event: | 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) |
| Location: | Nashville, TN, USA |
| Dates: | 10th-17th June 2025 |
| ISBN-13: | 979-8-3315-4364-8 |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1109/CVPR52734.2025.00682 |
| Publisher version: | https://doi.org/10.1109/cvpr52734.2025.00682 |
| 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 > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10215199 |
Archive Staff Only
 |
View Item |
