pyiqa.archs.afine_arch

A-FINE Model

github repo link: https://github.com/ChrisDud0257/AFINE

Cite as: @inproceedings{chen2025toward,

title={Toward Generalized Image Quality Assessment: Relaxing the Perfect Reference Quality Assumption}, author={Chen, Du and Wu, Tianhe and Ma, Kede and Zhang, Lei}, booktitle={Proceedings of the 2025 IEEE/CVF Computer Vision and Pattern Recognition Conference}, pages={12742–12752}, year={2025}

}

This file only support inferring A-FINE value. If you want to further train A-FINE, plase refer to https://github.com/ChrisDud0257/AFINE

Module Contents

pyiqa.archs.afine_arch.default_model_urls

pyiqa.archs.afine_arch.scale_finalscore(score, yita1=100, yita2=0, yita3=-1.971, yita4=-2.3734)

class pyiqa.archs.afine_arch.AFINEQhead(chns=(3, 768, 768, 768, 768, 768, 768, 768, 768, 768, 768, 768, 768), feature_out_channel=1, input_dim=768, hidden_dim=128, mean=(0.48145466, 0.4578275, 0.40821073), std=(0.26862954, 0.26130258, 0.27577711))

Bases: torch.nn.Module

forward(x, h_list_x)

class pyiqa.archs.afine_arch.AFINEDhead(chns=(3, 768, 768, 768, 768, 768, 768, 768, 768, 768, 768, 768, 768), mean=(0.48145466, 0.4578275, 0.40821073), std=(0.26862954, 0.26130258, 0.27577711))

Bases: torch.nn.Module

forward(x, y, h_list_x, h_list_y)

class pyiqa.archs.afine_arch.AFINENLM_NR_Fit(yita1=2, yita2=-2, yita3=3.7833, yita4=7.5676)

Bases: torch.nn.Module

forward(x)

class pyiqa.archs.afine_arch.AFINENLM_FR_Fit_with_limit(yita1=2, yita2=-2, yita3=-24.1335, yita4=8.1093, yita3_upper=-21, yita3_lower=-27, yita4_upper=9, yita4_lower=7)

Bases: torch.nn.Module

forward(x)

class pyiqa.archs.afine_arch.AFINELearnLambda(k=5)

Bases: torch.nn.Module

forward(x_nr, ref_nr, xref_fr)

class pyiqa.archs.afine_arch.AFINE(model_type='afine_all_scale', clip_backbone='ViT-B/32', step=32, num_patch=15, pretrained=True, pretrained_model_path=None, url_key='afine')

Bases: torch.nn.Module

forward(dis, ref=None)