IM-3D: iterative multiview diffusion and reconstruction for high-quality 3D generation
Most text-to-3D generators build upon off-the-shelf text-to-image models trained on billions of images. They use variants of Score Distillation Sampling (SDS), which is slow, somewhat unstable, and prone to artifacts. A mitigation is to fine-tune the 2D generator to be multi-view aware, which can he...
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Internet publication |
| Sprache: | English |
| Veröffentlicht: |
2024
|