HANDI generates hand-centric videos from an image and text prompt via automatic motion-area localization and a hand refinement loss.
Hrs-bench: Holistic, reliable and scalable benchmark for text-to-image models
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
background 1representative citing papers
citing papers explorer
-
HANDI: Hand-Centric Text-and-Image Conditioned Video Generation
HANDI generates hand-centric videos from an image and text prompt via automatic motion-area localization and a hand refinement loss.