How this analysis was created: This summary and feature list were written by an AI model that read the project's README and public documentation pages. Each feature links to the documentation it came from; stars, license and language come straight from the GitHub API. The model does not read the source code, and the analysis is refreshed when the project is re-analysed. Learn more on our About page.
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
Implementation of sub-Riemannian diffusion for image inpainting and enhancement
Early Accepted at MICCAI 2023 Pytorch Code of "InverseSR: 3D Brain MRI Super-Resolution Using a Latent Diffusion Model"
[NeurIPS 2023] PGDiff: Guiding Diffusion Models for Versatile Face Restoration via Partial Guidance
The main features of pq-yang/pgdiff are: Face Restoration, Inverse Problems.
Open-source alternatives to pq-yang/pgdiff include: zsyoaoa/difface — Zongsheng Yue, Chen Change Loy. xpixelgroup/diffbir — DiffBIR is a diffusion-based image restoration framework designed for blind image reconstruction. It utilizes… ballerin/v1diffusion — Implementation of sub-Riemannian diffusion for image inpainting and enhancement. chenxx89/bfrffusion. crosszamirski/guided-i2i — Combining image-to-image and class guided denoising diffusion probabilistic models. biomedai-ucsc/inversesr — [Early Accepted at MICCAI 2023] Pytorch Code of "InverseSR: 3D Brain MRI Super-Resolution Using a Latent Diffusion…
