Sem-Avatar: Semantic Controlled Neural Field for High-Fidelity Audio Driven Avatar.
Xiang ZhouWeichen ZhangYikang DingFan ZhouKai ZhangPublished in: PRCV (2) (2023)
Keyphrases
- high fidelity
- virtual world
- real time
- sign language
- neural network
- human computer interaction
- medical image compression
- virtual environment
- high quality
- domain specific
- network architecture
- multimedia
- real environment
- high resolution
- natural language
- visual information
- video conferencing
- multi modal
- semantic web
- human operators
- computer vision
- semantic context
- artificial intelligence