Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representation
–Neural Information Processing Systems
We present a novel alignment-before-generation approach to tackle the challenging task of generating general 3D shapes based on 2D images or texts.
Neural Information Processing Systems
Feb-17-2026, 18:22:19 GMT
- Country:
- Asia
- China > Shanghai
- Shanghai (0.05)
- Japan > Honshū
- Chūbu > Nagano Prefecture > Nagano (0.04)
- Middle East > Israel (0.04)
- China > Shanghai
- Europe
- Austria (0.04)
- Germany > Bavaria
- Upper Bavaria > Munich (0.04)
- Italy > Calabria
- Catanzaro Province > Catanzaro (0.04)
- North America > United States
- Illinois > Cook County > Chicago (0.04)
- Oceania > Australia
- Western Australia > Perth (0.04)
- South America > Chile
- Asia
- Technology: