BlindDPS/blind-dps
An official pytorch implementation of "Parallel Diffusion Model of Operator and Image for Blind Inverse Problems" (CVPR 2023)
This project helps scientists and researchers in image processing reconstruct clear images from blurry or distorted inputs where the cause of the blur is unknown. It takes a corrupted image and jointly estimates both the original sharp image and the specific blur (like motion blur or atmospheric turbulence) that degraded it. This is useful for anyone working with imaging systems where perfect conditions are impossible, such as astronomers, medical imagers, or remote sensing specialists.
129 stars. No commits in the last 6 months.
Use this if you need to restore clear images from blurry photographs or video frames, and you don't know the exact nature or parameters of the blur causing the degradation.
Not ideal if you already know the precise mathematical operation or filter that caused your image to be blurry; other methods might be more straightforward.
Stars
129
Forks
16
Language
Python
License
—
Category
Last pushed
Mar 02, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/BlindDPS/blind-dps"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
devzhk/InverseBench
InverseBench (ICLR 2025 spotlight)
guyyariv/DyPE
Official implementation for "DyPE: Dynamic Position Extrapolation for Ultra High Resolution Diffusion".
wyhuai/DDNM
[ICLR 2023 Oral] Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model
bahjat-kawar/ddrm
[NeurIPS 2022] Denoising Diffusion Restoration Models -- Official Code Repository
yuanzhi-zhu/DiffPIR
"Denoising Diffusion Models for Plug-and-Play Image Restoration", Yuanzhi Zhu, Kai Zhang,...