A real-world dataset of 99k drone camera trajectories and an autoregressive transformer, DVGFormer, learn to generate smooth, collision-avoiding camera movements without hand-crafted filming heuristics.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
method 1polarities
unclear 1representative citing papers
citing papers explorer
-
Learning Camera Movement Control from Real-World Drone Videos
A real-world dataset of 99k drone camera trajectories and an autoregressive transformer, DVGFormer, learn to generate smooth, collision-avoiding camera movements without hand-crafted filming heuristics.