VITON-DiT: Learning In-the-Wild Video Try-On from Human Dance Videos via Diffusion Transformers.
Jun ZhengFuwei ZhaoYoujiang XuXin DongXiaodan LiangPublished in: CoRR (2024)
Keyphrases
- video sequences
- learning process
- video data
- human activities
- video frames
- video streams
- video content
- online learning
- static images
- youtube videos
- video editing
- human learning
- video surveillance
- dynamic scenes
- moving camera
- multi view
- news video
- video annotation
- motion capture data
- reinforcement learning
- high definition
- multimedia
- learning algorithm