Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models.
Chenfei WuShengming YinWeizhen QiXiaodong WangZecheng TangNan DuanPublished in: CoRR (2023)
Keyphrases
- visual tasks
- visual information
- visual perception
- visual analysis
- real world
- low level
- probabilistic model
- visual features
- case study
- visual effects
- databases
- visual representations
- accurate models
- visual cues
- visual data
- mathematical models
- experimental data
- d objects
- prior knowledge
- keywords
- high level
- information retrieval