TianheWu/Assessor360
[NeurIPS 2023] Assessor360: Multi-sequence Network for Blind Omnidirectional Image Quality Assessment
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.
Stars
37
Forks
2
Language
Python
License
MIT
Category
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.
Higher-rated alternatives
krshrimali/No-Reference-Image-Quality-Assessment-using-BRISQUE-Model
Implementation of the paper "No Reference Image Quality Assessment in the Spatial Domain" by A...
VQAssessment/FAST-VQA-and-FasterVQA
[ECCV2022, TPAMI2023] FAST-VQA, and its extended version FasterVQA.
IIGROUP/MANIQA
[CVPRW oral 2022] MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment
pterhoer/FaceImageQuality
Code and information for face image quality assessment with SER-FIQ
vztu/RAPIQUE
[IEEE OJSP'2021] "RAPIQUE: Rapid and Accurate Video Quality Prediction of User Generated...