ModelCard.md

Model Cards for IQA-PyTorch

General FR/NR Methods

List all model names with:

import pyiqa
print(pyiqa.list_models())

FR Method	Model names	Description
TOPIQ	topiq_fr, topiq_fr-pipal	Proposed in this paper
AHIQ	ahiq
PieAPP	pieapp
LPIPS	lpips, lpips-vgg, stlpips, stlpips-vgg, lpips+, lpips-vgg+
DISTS	dists
WaDIQaM	wadiqam_fr
CKDN1	ckdn
FSIM	fsim
SSIM	ssim, ssimc	Gray input (y channel), color input
MS-SSIM	ms_ssim
CW-SSIM	cw_ssim
PSNR	psnr, psnry	Color input, gray input (y channel)
VIF	vif
GMSD	gmsd
NLPD	nlpd
VSI	vsi
MAD	mad

NR Method	Model names	Description
Q-Align	qalign (with quality[default], aesthetic options)	Large vision-language models
QualiCLIP(+)	qualiclip, qualiclip+, qualiclip+-clive, qualiclip+-flive, qualiclip+-spaq	QualiCLIP(+) with different datasets, koniq by default
LIQE	liqe, liqe_mix	CLIP based method
ARNIQA	arniqa, arniqa-live, arniqa-csiq, arniqa-tid, arniqa-kadid, arniqa-clive, arniqa-flive, arniqa-spaq	ARNIQA with different datasets, koniq by default
TOPIQ	topiq_nr, topiq_nr-flive, topiq_nr-spaq	TOPIQ with different datasets, koniq by default
TReS	tres, tres-flive	TReS with different datasets, koniq by default
FID	fid	Statistic distance between two datasets
CLIPIQA(+)	clipiqa, clipiqa+, clipiqa+_vitL14_512,clipiqa+_rn50_512	CLIPIQA(+) with different backbone, RN50 by default
MANIQA	maniqa, maniqa-kadid, maniqa-pipal	MUSIQ with different datasets, koniq by default
MUSIQ	musiq, musiq-spaq, musiq-paq2piq, musiq-ava	MUSIQ with different datasets, koniq by default
DBCNN	dbcnn
PaQ-2-PiQ	paq2piq
HyperIQA	hyperiqa
NIMA	nima, nima-vgg16-ava	Aesthetic metric trained with AVA dataset
WaDIQaM	wadiqam_nr
CNNIQA	cnniqa
NRQM(Ma)2	nrqm	No backward
PI(Perceptual Index)	pi	No backward
BRISQUE	brisque, brisque_matlab	No backward
ILNIQE	ilniqe	No backward
NIQE	niqe, niqe_matlab	No backward
PIQE	piqe	No backward

[1] This method use distorted image as reference. Please refer to the paper for details.
[2] Currently, only naive random forest regression is implemented and does not support backward.

IQA Methods for Specific Tasks

Task	Method	Description
Color IQA	msswd	Perceptual color difference metric MS-SWD, ECCV2024, Arxiv, Github
Face IQA	topiq_nr-face	TOPIQ model trained with face IQA dataset (GFIQA)
Underwater IQA	uranker	A ranking-based underwater image quality assessment (UIQA) method, AAAI2023, Arxiv, Github

Metric Output Score Range

Note: ~ means that the corresponding numeric bound is typical value and not mathematically guaranteed

You can now access the rough output range of each metric like this:

metric = pyiqa.create_metric('lpips')
print(metric.score_range)