DreamFusion
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Text-to-Object Generation | DreamFusion prompts | CLIP Image-Text Similarity0.296 | 9 | |
| Multi-view Consistency | DreamFusion 414 text prompts (test) | Avg MRC12.22 | 7 | |
| Multi-view Reconstruction | DreamFusion (test) | Avg MRC0.1222 | 7 | |
| Text-to-3D Generation | DreamFusion prompt gallery (test) | CLIP Score65.9 | 6 | |
| Text-to-3D Generation | DreamFusion 400 text prompts (test) | CLIP Score (ViT-L/14)27.39 | 4 | |
| Text-to-3D Generation | DreamFusion 50 text prompts | CLIP Similarity26.8 | 4 | |
| Text-to-3D generation | DreamFusion prompts (397) | Preference (Realistic)58.3 | 1 |
Showing 7 of 7 rows