GOEnFusion: gradient origin encodings for 3D forward diffusion models
The recently introduced Forward-Diffusion method allows to train a 3D diffusion model using only 2D images for supervision. However, it does not easily generalise to different 3D representations and requires a computationally expensive auto-regressive sampling process to generate the underlying 3D s...
| Main Authors: | , , , |
|---|---|
| Formato: | Internet publication |
| Idioma: | English |
| Publicado em: |
2023
|