miccunifi/ARNIQA
[WACV 2024 Oral] - ARNIQA: Learning Distortion Manifold for Image Quality Assessment
ARNIQA helps image professionals automatically assess the quality of digital images without needing a perfect reference image. It takes a degraded image as input and outputs a quality score from 0 to 1, indicating how a human would perceive its quality. This tool is for anyone who needs to quickly evaluate and compare the perceptual quality of many images, such as photo editors, quality control specialists, or content managers.
150 stars. No commits in the last 6 months.
Use this if you need to objectively measure the human-perceived quality of images that might have various distortions like blur, noise, or compression artifacts, especially when no original, pristine version is available for comparison.
Not ideal if you need to detect very specific, technical image flaws or if your primary goal is pixel-perfect restoration rather than a subjective quality score.
Stars
150
Forks
5
Language
Python
License
Apache-2.0
Category
Last pushed
Jul 31, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/miccunifi/ARNIQA"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
clovaai/synthtiger
Official Implementation of SynthTIGER (Synthetic Text Image Generator), ICDAR 2021
ocampor/image-quality
Image quality is an open source software library for Image Quality Assessment (IQA).
idealo/image-quality-assessment
Convolutional Neural Networks to predict the aesthetic and technical quality of images.
hzwer/ICCV2019-LearningToPaint
ICCV2019 - Learning to Paint With Model-based Deep Reinforcement Learning
onuralpszr/GFPGAN-ncnn-vulkan
[WIP] NCNN with Vulkan implementation of GFPGAN aims at developing Practical Algorithms for...