ZehaoDou-official/FPS-SMC-2023
Official Pytorch repository for "Diffusion Posterior Sampling for Linear Inverse Problem Solving: A Filtering Perspective", where FPS (Filtering Posterior Sampling) as well as its extension FPS-SMC are proposed.
This tool helps recover high-quality images from degraded versions, such as blurry, low-resolution, or partially obscured photos. You input a damaged image and specify the type of damage (e.g., motion blur, low resolution), and it outputs a restored, clearer image. Image processing specialists, digital artists, or anyone needing to enhance image quality from imperfect sources would find this useful.
No commits in the last 6 months.
Use this if you need to precisely reconstruct details in images that have suffered from common degradations like blur, low resolution, or missing parts, and you require state-of-the-art results without retraining complex models.
Not ideal if you are looking for a simple, point-and-click image editor for casual photo touch-ups rather than a specialized, high-fidelity image reconstruction tool.
Stars
50
Forks
12
Language
Python
License
—
Category
Last pushed
Aug 06, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/ZehaoDou-official/FPS-SMC-2023"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
xie-lab-ml/Golden-Noise-for-Diffusion-Models
[ICCV2025] The code of our work "Golden Noise for Diffusion Models: A Learning Framework".
yulewang97/ERDiff
[NeurIPS 2023 Spotlight] Official Repo for "Extraction and Recovery of Dpatio-temporal Structure...
UNIC-Lab/RadioDiff
This is the code for the paper "RadioDiff: An Effective Generative Diffusion Model for...
pantheon5100/pid_diffusion
This repository is the official implementation of the paper: Physics Informed Distillation for...
zju-pi/diff-sampler
An open-source toolbox for fast sampling of diffusion models. Official implementations of our...