Projects sharing features with Diffusion Posterior Sampling

The repository contains reproducible PyTorch source code of our paper Solving Linear Inverse Problems Provably via Posterior Sampling with Latent Diffusion Models. We present the first framework to solve general inverse problems leveraging pre-trained latent diffusion models. Previously proposed…

DiffBIR is a diffusion-based image restoration framework designed for blind image reconstruction. It utilizes generative diffusion priors to recover high-quality images from sources with unknown or complex degradations without requiring explicit degradation models. The system includes specialized models for face restoration, enabling the recovery of facial landmarks, textures, and backgrounds in degraded portraits. To support high-resolution outputs on hardware with limited memory, it employs a tiled image upscaler that divides images into smaller patches during sampling. The framework cover

Zongsheng Yue, Jianyi Wang, Chen Change Loy

arXiv | PDF | Project Website

Official implementation of Paper "Rethinking Video Deblurring with Wavelet-Aware Dynamic Transformer and Diffusion Model" (ECCV 2024)

Jiezhang Cao, Yue Shi, Kai Zhang, Yulun Zhang, Radu Timofte, Luc Van Gool

CVPR 2025 Reconciling Stochastic and Deterministic Strategies for Zero-shot Image Restoration using Diffusion Model in Dual, PyTorch Implementation

Combining image-to-image and class guided denoising diffusion probabilistic models.

AAAI 2026 PerTouch: VLM-Driven Agent for Personalized and Semantic Image Retouching

Project Page | Paper | Model Card 🤗

The code and pre-trained models of the paper "Image Deblurring based on Diffusion Models" will be released in this repository.

PyTorch Implementation of introducing diffusion approach to 3D depth perception ECCV 2024

Official code for Zero-Reference Low-Light Enhancement via Physical Quadruple Priors (CVPR-24)

Diffusion model-based inverse problem solvers have demonstrated state-of-the-art performance in cases where the forward operator is known (i.e. non-blind). However, the applicability of the method to blind inverse problems has yet to be explored. In this work, we show that we can indeed solve a…

CVPR 2024 oralThis repository contains the official implementation of "FlowIE: Efficient Image Enhancement via Rectified Flow"

This is the official implementation of InstaRevive: One-Step Image Enhancement via Dynamic Score Matching

SUPIR is an AI image upscaler and restoration system designed to remove artifacts and restore quality to real-world photographs. It functions as a diffusion-based image enhancer and restoration tool that uses large-scale model scaling to produce high-resolution results with photorealistic details. The system balances visual aesthetics with input fidelity, allowing for a trade-off between strict adherence to the original image and the overall visual appeal of the output. It leverages large-scale model inference to improve image clarity and maintain realistic details during the upscaling proces

[Paper](https://arxiv.org/abs/2304.01247) [Project Page](https://generativediffusionprior.github.io/)

Inpaint-Anything is a diffusion-based image editor and inpainting tool designed to remove or replace objects in images, videos, and 3D scenes. It functions as a text-guided manipulator that uses natural language descriptions and mask-based filling to modify visual content. The system provides specialized capabilities for multi-view 3D scene editing and video object removal. It tracks selected objects across multiple frames or perspectives to synthesize consistent backgrounds and maintain spatial coherence after an element is removed. The tool covers a range of image manipulation tasks, inclu

(† Co-first Author, Corresponding Author)

ICCV 2025 FoundIR: Unleashing Million-scale Training Data to Advance Foundation Models for Image Restoration

ACM Multimedia 2022 Delving Globally into Texture and Structure for Image Inpainting

NeurIPS2024: Diffusion Priors for Variational Likelihood Estimation and Image Denoising

Official implementation of Cold-Diffusion for different transformations in pytorch.