TianheWu/Assessor360

[NeurIPS 2023] Assessor360: Multi-sequence Network for Blind Omnidirectional Image Quality Assessment

29
/ 100
Experimental

This project helps evaluate the visual quality of 360-degree virtual reality (VR) images without needing a perfect reference image. You input an omnidirectional image that might have distortions, and it outputs a score representing its perceived quality. VR content creators, designers, and quality assurance specialists can use this to quickly assess and improve their immersive visual experiences.

No commits in the last 6 months.

Use this if you need an objective way to grade the quality of 360-degree VR images, especially when you don't have an original, pristine version for comparison.

Not ideal if you are working with standard 2D images or require a quality assessment method that compares against a reference image.

virtual-reality 360-degree-imaging image-quality-assessment VR-content-creation immersive-media
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 6 / 25

How are scores calculated?

Stars

37

Forks

2

Language

Python

License

MIT

Last pushed

Oct 11, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/TianheWu/Assessor360"

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