TETO: Tracking Events with Teacher Observation for Motion Estimation and Frame Interpolation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917360123772928 |
|---|---|
| author | Yang, Jini Hong, Eunbeen Son, Soowon Lee, Hyunkoo Hong, Sunghwan Kim, Sunok Kim, Seungryong |
| author_facet | Yang, Jini Hong, Eunbeen Son, Soowon Lee, Hyunkoo Hong, Sunghwan Kim, Sunok Kim, Seungryong |
| contents | Event cameras capture per-pixel brightness changes with microsecond resolution, offering continuous motion information lost between RGB frames. However, existing event-based motion estimators depend on large-scale synthetic data that often suffers from a significant sim-to-real gap. We propose TETO (Tracking Events with Teacher Observation), a teacher-student framework that learns event motion estimation from only $\sim$25 minutes of unannotated real-world recordings through knowledge distillation from a pretrained RGB tracker. Our motion-aware data curation and query sampling strategy maximizes learning from limited data by disentangling object motion from dominant ego-motion. The resulting estimator jointly predicts point trajectories and dense optical flow, which we leverage as explicit motion priors to condition a pretrained video diffusion transformer for frame interpolation. We achieve state-of-the-art point tracking on EVIMO2 and optical flow on DSEC using orders of magnitude less training data, and demonstrate that accurate motion estimation translates directly to superior frame interpolation quality on BS-ERGB and HQ-EVFI. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_23487 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | TETO: Tracking Events with Teacher Observation for Motion Estimation and Frame Interpolation Yang, Jini Hong, Eunbeen Son, Soowon Lee, Hyunkoo Hong, Sunghwan Kim, Sunok Kim, Seungryong Computer Vision and Pattern Recognition Event cameras capture per-pixel brightness changes with microsecond resolution, offering continuous motion information lost between RGB frames. However, existing event-based motion estimators depend on large-scale synthetic data that often suffers from a significant sim-to-real gap. We propose TETO (Tracking Events with Teacher Observation), a teacher-student framework that learns event motion estimation from only $\sim$25 minutes of unannotated real-world recordings through knowledge distillation from a pretrained RGB tracker. Our motion-aware data curation and query sampling strategy maximizes learning from limited data by disentangling object motion from dominant ego-motion. The resulting estimator jointly predicts point trajectories and dense optical flow, which we leverage as explicit motion priors to condition a pretrained video diffusion transformer for frame interpolation. We achieve state-of-the-art point tracking on EVIMO2 and optical flow on DSEC using orders of magnitude less training data, and demonstrate that accurate motion estimation translates directly to superior frame interpolation quality on BS-ERGB and HQ-EVFI. |
| title | TETO: Tracking Events with Teacher Observation for Motion Estimation and Frame Interpolation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.23487 |