IDOL: Unified Dual-Modal Latent Diffusion for Human-Centric Joint Video-Depth Generation.
Yuanhao ZhaiKevin LinLinjie LiChung-Ching LinJianfeng WangZhengyuan YangDavid S. DoermannJunsong YuanZicheng LiuLijuan WangPublished in: CoRR (2024)
Keyphrases
- human centric
- human centered
- video data
- video sequences
- multimedia
- video content
- context awareness
- e government
- context aware
- human computer interaction
- multimedia data
- video frames
- depth map
- latent variables
- information retrieval
- ambient intelligence
- depth information
- space time
- multi modal
- image sequences
- individual user
- information systems