StableNormal: Reducing Diffusion Variance for Stable and Sharp Normal

This repository represents the official implementation of the paper titled "Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation".

Website Paper Hugging Face Space Hugging Face Model License

We propose StableNormal, which tailors the diffusion priors for monocular normal estimation. Unlike prior diffusion-based works, we focus on enhancing estimation stability by reducing the inherent stochasticity of diffusion models ( i.e. , Stable Diffusion). This enables “Stable-and-Sharp” normal estimation, which outperforms multiple baselines (try Compare), and improves various real-world applications (try Demo).

teaser