wyhuai/DDNM
A denoising diffusion null-space model that performs various image restoration tasks (denoising, super-resolution, inpainting, colorization, deblurring) without any training or optimization.
Not currently ranked — collecting fresh signals.
star history
DDNM solves image restoration problems by leveraging the null-space of the degradation operator combined with pre-trained denoising diffusion models. Users provide a degraded image and specify the restoration task (e.g., denoising, super-resolution), and the method iteratively refines the result without requiring any training on specific degradation pairs. The approach works across arbitrary image sizes and supports applications including old photo restoration, compressed sensing, and blind inpainting.
Frequently asked
- What is wyhuai/DDNM?
- A denoising diffusion null-space model that performs various image restoration tasks (denoising, super-resolution, inpainting, colorization, deblurring) without any training or optimization.
- Is DDNM open source?
- Yes — wyhuai/DDNM is open source, released under the MIT license.
- What language is DDNM written in?
- wyhuai/DDNM is primarily written in Python.
- How popular is DDNM?
- wyhuai/DDNM has 1.3k stars on GitHub.
- Where can I find DDNM?
- wyhuai/DDNM is on GitHub at https://github.com/wyhuai/DDNM.