---
pipeline_tag: depth-estimation
library_name: diffusers
---

# GeoNeXt

**Video Generative Models as Geometry Learner**

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.

- **Paper**: [Video Generative Models as Geometry Learner](https://huggingface.co/papers/2608.28549)
- **Project page**: [https://happy-hsy.github.io/projects/GeoNeXt/](https://happy-hsy.github.io/projects/GeoNeXt/)
- **GitHub**: [https://github.com/Creative-Intelligence-Studio/GeoNeXt](https://github.com/Creative-Intelligence-Studio/GeoNeXt)
- **Model checkpoints**: [happy0612/GeoNeXt](https://huggingface.co/happy0612/GeoNeXt)

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.