A pose-to-video system for sign language that uses SMPL-X avatar retargeting plus ControlNet and an IP-Adapter image prompt to generate customizable synthetic signers with more consistent appearance.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DiffSign: AI-Assisted Generation of Customizable Sign Language Videos With Enhanced Realism
A pose-to-video system for sign language that uses SMPL-X avatar retargeting plus ControlNet and an IP-Adapter image prompt to generate customizable synthetic signers with more consistent appearance.