GenDoP: Auto-regressive Camera Trajectory Generation as a Director of Photography
Source: https://arxiv.org/abs/2504.07083
Structured fields
{
"checked_at": "2026-10-17T00:00:00.000Z",
"usefulness": "DataDoP: 29K real shots with camera trajectories, depth and captions describing movement, scene interaction and directorial intent; GenDoP generates camera moves from text and RGBD. Relevant to encoding camera movement with its purpose.",
"source_type": "paper",
"availability": "available",
"source_owner": "Zhang, Wu, Tan, Liu, Wetzstein, Lin",
"next_check_at": "2026-10-31T00:00:00.000Z",
"upstream_updated_at": "2025-04-10T00:00:00.000Z"
}Evidence claims
- [upstream_claim] DataDoP: 29K real-world shots with camera trajectories, depth maps and detailed captions covering movement, scene interaction and directorial intent; GenDoP is an auto-regressive decoder-only Transformer. · locator: abstract source
- [sourced_fact] Project website kszpxxzmc.github.io/GenDoP; arXiv non-exclusive license. · locator: abstract page links and license source
- [upstream_claim] Research review verdict at export: reviewed (as of 2026-10-17). Recorded by the research pipeline, not a hub review outcome; evidence.review stays unreviewed until an independent reviewer records one.
Rights
| component | license | hosting | redistribution | modification | training | Evidence and notes |
|---|---|---|---|---|---|---|
| documentation | arXiv-nonexclusive-distrib-1.0 | restricted | restricted | unknown | unknown | Paper only; dataset and code licenses not on the abstract page. |