Stars
Demos for tutorial on inverse problems
Image Restoration Toolbox (PyTorch). Training and testing codes for DPIR, USRNet, DnCNN, FFDNet, SRMD, DPSR, BSRGAN, SwinIR
Pytorch Implementation (unofficial) of the paper "Mean Flows for One-step Generative Modeling" by Geng et al.
A collection of awesome text-to-image generation studies.
Python best practices guidebook, written for humans.
source code for the "ProxiMO: Proximal Multi-Operator Networks for Quantitative Susceptibility Mapping" paper, presented in MICCAI 2024
😸 Soothing pastel theme for the high-spirited!
Python Fire is a library for automatically generating command line interfaces (CLIs) from absolutely any Python object.
Video+code lecture on building nanoGPT from scratch
Paper Reimplementation —— "D. P. Kingma and M. Welling. Auto-Encoding Variational Bayes. ICLR, 2014."
🧠💬 Articles I wrote about machine learning, archived from MachineCurve.com.
Technically-oriented PDF Collection (Papers, Specs, Decks, Manuals, etc)
Refine high-quality datasets and visual AI models
A beautiful, simple, clean, and responsive Jekyll theme for academics
Official repo for consistency models.
A beautiful, simple, clean, and responsive Jekyll theme for academics
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
Segment Anything in Medical Images
Plug-and-Play Image Restoration with Deep Denoiser Prior (IEEE TPAMI 2021) (PyTorch)
SwinIR: Image Restoration Using Swin Transformer (official repository)
Visualizer for neural network, deep learning and machine learning models
Examples and code for "Solving linear inverse problems using the prior implicit in a denoiser", Z Kadkhodaie and EP Simoncelli
[NeurIPS 2021] SNIPS: Solving Noisy Inverse Problems Stochastically
Code to reproduce results from "Invertible generative models for inverse problems: mitigating representation error and dataset bias"
Image-to-Image Translation in PyTorch