SCoPE: Sightline-Coordinate Positional Encoding for Video Diffusion Transformers
Video diffusion transformers address their tokens by position on the pixel-time grid: an address in the tensor, not in the world. The address we would want, the world point a token depicts, lies on a surface not yet generated, while its camera ray is fixed once the user specifies a trajectory. SCoPE therefore treats the ray as a second positional coordinate, and camera control becomes a property of the coordinate system, not an added module. The ray is added to the pretrained attention's queries and keys, and the score gains a term that reads the two rays alone. Its canonical form, the reciprocal product of line geometry, measures how nearly two lines of sight meet. Normalize-Gate-Inject ...
| Authors | Minghao Yin, Jiahao Lu, Wenbo Hu et al. |
|---|---|
| Primary category | cs.CV |
| Published | 25 June 2026 |
| Last updated at source | 12 August 2026 |
Connected in the knowledge graph
- Michaelqaz/SCoPE-GalleryDataset · cited by
Models and datasets referencing this paper
- Michaelqaz/SCoPE-GalleryDataset
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 Information may be incomplete or out of date.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.