gbymat/DiffHDR-pytorch

This is the official PyTorch implementation for DiffHDR: Towards High-quality HDR Deghosting with Conditional Diffusion Models (TCSVT'2023)

18
/ 100
Experimental

When merging multiple bracketed photos into a single High Dynamic Range (HDR) image, motion in the scene can cause blurry or 'ghosting' artifacts. This tool takes a set of bracketed Low Dynamic Range (LDR) images, even with movement, and outputs a high-quality, ghost-free HDR image. It's designed for professional photographers, CGI artists, and anyone creating HDR content from real-world scenes.

No commits in the last 6 months.

Use this if you need to create a high-quality HDR image from a series of bracketed LDR photos where there was significant motion or saturation.

Not ideal if you're looking for a simple point-and-shoot HDR solution, as this tool requires a technical setup and understanding of image processing workflows.

HDR imaging computational photography image deghosting photo editing digital imaging
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 4 / 25

How are scores calculated?

Stars

21

Forks

1

Language

Python

License

Last pushed

Feb 12, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/gbymat/DiffHDR-pytorch"

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