ZohebAbai/tf-focal-frequency-loss

Tensorflow Implementation of Focal Frequency Loss for Image Reconstruction and Synthesis [ICCV 2021]

38
/ 100
Emerging

This is a tool for machine learning researchers and engineers working on image generation and reconstruction. It takes a generated image and a real image as input, then calculates a 'focal frequency loss' to help your generative model produce more realistic images. The output is a loss value that guides your model to better synthesize image details, especially in the frequency domain. It's for those developing or fine-tuning models like VAE, pix2pix, or StyleGAN2.

No commits in the last 6 months. Available on PyPI.

Use this if you are developing or training a deep learning model for image reconstruction or synthesis and want to improve the perceptual quality and detail of the generated images.

Not ideal if you are a practitioner looking for a ready-to-use application to process images, rather than a component for building generative models.

image-synthesis image-reconstruction generative-models deep-learning-research computer-vision-engineering
Stale 6m
Maintenance 0 / 25
Adoption 5 / 25
Maturity 25 / 25
Community 8 / 25

How are scores calculated?

Stars

9

Forks

1

Language

Python

License

MIT

Category

gan-based-t2i

Last pushed

May 30, 2022

Commits (30d)

0

Dependencies

1

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/ZohebAbai/tf-focal-frequency-loss"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.