Temporally Grounded Compositional Camera Motion Understanding via Geometric Knowledge Distillation
Understanding camera motion is fundamental to video perception, with applications in spatial intelligence and controllable video generation. Multimodal large language models (MLLMs) provide a natural interface for this task, but existing work typically assigns one or more labels to an entire clip. Such clip-level recognition overlooks two defining properties of real camera motion: it can change within a shot, and multiple movements can occur simultaneously. We therefore formulate camera-motion understanding as temporally grounded, compositional recognition, which requires a model to localize motion-consistent intervals and identify every movement active within each interval. We introduce ...
| Authors | Dazhao Du, Shiyan Du, Jian Liu et al. |
|---|---|
| Primary category | cs.CV |
| Published | 11 August 2026 |
| Last updated at source | 11 August 2026 |
Connected in the knowledge graph
- ddz16/CamDistill-8BModel · cited by
Models and datasets referencing this paper
- ddz16/CamDistill-8BModel
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 Information may be incomplete or out of date.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.