Direct2.5: Diverse Text-to-3D Generation via Multi-view 2.5D Diffusion.
Yuanxun LuJingyang ZhangShiwei LiTian FangDavid McKinnonYanghai TsinLong QuanXun CaoYao YaoPublished in: CoRR (2023)
Keyphrases
- multi view
- single view
- multiple views
- depth map
- d objects
- three dimensional
- multiple cameras
- bundle adjustment
- camera calibration
- stereo video
- range images
- multi view images
- multi view stereo
- view synthesis
- surface reconstruction
- multi view reconstruction
- scene flow estimation
- semi supervised
- co training
- text mining
- high quality
- image quality
- multiple viewpoints
- multi view learning
- face recognition