mlvlab/DAVI

Official Implementation (Pytorch) of "DAVI: Diffusion Prior-Based Amortized Variational Inference for Noisy Inverse Problems", ECCV 2024 Oral paper

33
/ 100
Emerging

This project helps image restoration professionals efficiently reconstruct high-quality images from noisy or incomplete measurements. It takes a degraded image (e.g., blurry, low-resolution, or with missing parts) and quickly outputs a clear, complete, and restored version. Scientists, medical imaging specialists, and digital artists would find this useful for tasks like deblurring, super-resolution, inpainting, denoising, and colorization.

No commits in the last 6 months.

Use this if you need to restore multiple types of degraded images, such as blurry photos, low-resolution scans, or images with missing sections, with high efficiency and without needing to optimize for each new image.

Not ideal if your image restoration needs are outside of the supported degradation types (deblurring, super-resolution, inpainting, denoising, colorization) or if you require real-time processing on embedded devices.

image-restoration computational-photography medical-imaging digital-art computer-vision
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

74

Forks

4

Language

Python

License

MIT

Last pushed

Aug 16, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/mlvlab/DAVI"

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