Guiding a pre-trained image-to-video model with hand-designed energy functions discovers multiple distinct, object-focused motions from a single image, without training.
Mitra, Kuldeep Kulkarni, Chun- Hao Paul Huang, Tuanfeng Y
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Motion Modes: What Could Happen Next?
Guiding a pre-trained image-to-video model with hand-designed energy functions discovers multiple distinct, object-focused motions from a single image, without training.