HifiDiff: High-fidelity diffusion model for face hallucination from tiny non-frontal faces (Neurocomputing 2025)

This repository contains an unofficial code implementation of HifiDiff, a joint face super-resolution and frontalization model.

🚀 Getting Started

Please refer to requirements.txt for all packages.

Name		Name	Last commit message	Last commit date
Latest commit History 70 Commits
models		models
.gitignore		.gitignore
README.md		README.md
dataset.py		dataset.py
infer_cr.py		infer_cr.py
pretrain_denoiser.py		pretrain_denoiser.py
pretrain_idc.py		pretrain_idc.py
requirements.txt		requirements.txt
run.py		run.py
test_idc.py		test_idc.py
test_refiner.py		test_refiner.py
train_cr.py		train_cr.py
train_refiner.py		train_refiner.py
utils.py		utils.py