Algolzw/image-restoration-sde
PyTorch implementation of diffusion models using mean-reverting stochastic differential equations for comprehensive image restoration tasks.
Not currently ranked — collecting fresh signals.
star history
This repository provides official implementations of IR-SDE and Refusion, two diffusion-based image restoration methods. IR-SDE uses mean-reverting stochastic differential equations to model the restoration process, while Refusion enables large-size realistic image restoration using latent-space diffusion models. Both approaches handle tasks including deblurring, denoising, super-resolution, deraining, dehazing, inpainting, and shadow removal. The methods are trained on synthetic and real-world datasets and achieved state-of-the-art results, winning the NTIRE 2023 Image Shadow Removal Challenge.
Frequently asked
- What is Algolzw/image-restoration-sde?
- PyTorch implementation of diffusion models using mean-reverting stochastic differential equations for comprehensive image restoration tasks.
- Is image-restoration-sde open source?
- Yes — Algolzw/image-restoration-sde is open source, released under the MIT license.
- What language is image-restoration-sde written in?
- Algolzw/image-restoration-sde is primarily written in Python.
- How popular is image-restoration-sde?
- Algolzw/image-restoration-sde has 720 stars on GitHub.
- Where can I find image-restoration-sde?
- Algolzw/image-restoration-sde is on GitHub at https://github.com/Algolzw/image-restoration-sde.