Dual3D: Efficient and Consistent Text-to-3D Generation with Dual-mode Multi-view Latent Diffusion.
Xinyang LiZhangyu LaiLinning XuJianfei GuoLiujuan CaoShengchuan ZhangBo DaiRongrong JiPublished in: CoRR (2024)
Keyphrases
- multi view
- single view
- multiple views
- three dimensional
- depth map
- camera calibration
- multiple cameras
- semi supervised
- multi view clustering
- d objects
- multi view reconstruction
- multi view learning
- view synthesis
- co training
- viewpoint
- multi view images
- light field
- similarity measure
- range images
- visual hull
- computer vision
- scene reconstruction
- multi view stereo
- video sequences
- free viewpoint
- object recognition
- machine learning