EndlessSora/focal-frequency-loss

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

51
/ 100
Established

This project helps improve the quality of generated or reconstructed images, like those used in digital art, virtual try-on, or visual effects. It takes an image generation model's output and a target image, then refines the output to better match the fine details and textures of real images. This is for researchers and practitioners working with image synthesis and reconstruction models.

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

Use this if you are developing or training image generation models (like VAE, pix2pix, or StyleGAN2) and want to enhance the realism, sharpness, or textural quality of the output images.

Not ideal if you are looking for a tool to perform basic image editing, object detection, or classification, as this is specifically designed to refine the output of generative models.

image-synthesis image-reconstruction generative-AI digital-imaging computer-vision
Stale 6m
Maintenance 0 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 16 / 25

How are scores calculated?

Stars

706

Forks

63

Language

Python

License

MIT

Last pushed

Aug 21, 2024

Commits (30d)

0

Dependencies

2

Get this data via API

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

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