bahjat-kawar/ddrm
A research implementation of DDRM, a method that leverages pre-trained denoising diffusion models to solve image restoration tasks like deblurring, inpainting, and super-resolution.
Not currently ranked — collecting fresh signals.
star history
This repository contains the official implementation of the DDRM paper from NeurIPS 2022. It adapts pre-trained DDPMs (Denoising Diffusion Probabilistic Models) to solve general linear inverse problems in image restoration without requiring task-specific supervised training. The method uses the generative prior of diffusion models to perform efficient restoration across different tasks including deblurring, inpainting, and super-resolution, working directly with off-the-shelf pretrained models from OpenAI and other sources.
Frequently asked
- What is bahjat-kawar/ddrm?
- A research implementation of DDRM, a method that leverages pre-trained denoising diffusion models to solve image restoration tasks like deblurring, inpainting, and super-resolution.
- Is ddrm open source?
- Yes — bahjat-kawar/ddrm is open source, released under the MIT license.
- What language is ddrm written in?
- bahjat-kawar/ddrm is primarily written in Python.
- How popular is ddrm?
- bahjat-kawar/ddrm has 668 stars on GitHub.
- Where can I find ddrm?
- bahjat-kawar/ddrm is on GitHub at https://github.com/bahjat-kawar/ddrm.