TrajLoom: Dense Future Trajectory Generation from Video
Predicting future motion is crucial in video understanding and controllable video generation. Dense point trajectories are a compact, expressive motion representation, but modeling their future evolution from observed video remains challenging. We propose a framework that predicts future trajectories and visibility from past trajectories and video context. Our method has three components: (1) Grid-Anchor Offset Encoding, which reduces location-dependent bias by representing each point as an offset from its pixel-center anchor; (2) TrajLoom-VAE, which learns a compact spatiotemporal latent space for dense trajectories with masked reconstruction and a spatiotemporal consistency regularizer;...
| Authors | Zewei Zhang, Jia Jun Cheng Xian, Kaiwen Liu et al. |
|---|---|
| Primary category | cs.CV |
| Published | 23 March 2026 |
| Last updated at source | 23 March 2026 |
Connected in the knowledge graph
- zeweizhang/TrajLoomDatasetsDataset · cited by
Models and datasets referencing this paper
- zeweizhang/TrajLoomDatasetsDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.