Add model card (#1)
Browse files- Add model card (44300e892187db0d25033b1ddbddf9297ec71384)
Co-authored-by: Niels Rogge <nielsr@users.noreply.huggingface.co>
README.md
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
pipeline_tag: depth-estimation
|
| 3 |
+
library_name: diffusers
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# GeoNeXt
|
| 7 |
+
|
| 8 |
+
**Video Generative Models as Geometry Learner**
|
| 9 |
+
|
| 10 |
+
GeoNeXt is a unified framework for monocular depth and surface normal estimation, repurposing pretrained video generative models for geometry prediction through a next-frames formulation.
|
| 11 |
+
|
| 12 |
+
- **Paper**: [Video Generative Models as Geometry Learner](https://huggingface.co/papers/2608.28549)
|
| 13 |
+
- **Project page**: [https://happy-hsy.github.io/projects/GeoNeXt/](https://happy-hsy.github.io/projects/GeoNeXt/)
|
| 14 |
+
- **GitHub**: [https://github.com/Creative-Intelligence-Studio/GeoNeXt](https://github.com/Creative-Intelligence-Studio/GeoNeXt)
|
| 15 |
+
- **Model checkpoints**: [happy0612/GeoNeXt](https://huggingface.co/happy0612/GeoNeXt)
|
| 16 |
+
|
| 17 |
+
The repository contains checkpoints for GeoNeXt-Wan and GeoNeXt-SVD. Follow the instructions in the GitHub repository to run inference for depth and normal estimation.
|