👁️ 🖼️ 🔥PyTorch Toolbox for Image Quality Assessment, including LPIPS, FID, NIQE, NRQM(Ma), MUSIQ, TOPIQ, NIMA, DBCNN, BRISQUE, PI and more...

A comprehensive collection of IQA papers

[CVPR2023] Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective

Quality-Aware Image-Text Alignment for Real-World Image Quality Assessment

[WACV 2024 Oral] - ARNIQA: Learning Distortion Manifold for Image Quality Assessment

[ICME2024, Official Code] for paper "Bringing Textual Prompt to AI-Generated Image Quality Assessment"

Official implementation of our IEEE Access paper (2024), ZEN-IQA: Zero-Shot Explainable and No-Reference Image Quality Assessment with Vision Language Model

Official implementation for "Image Quality Assessment using Contrastive Learning"

Official implementation for CVPR2023 Paper "Re-IQA : Unsupervised Learning for Image Quality Assessment in the Wild"

The repository for 'Uncertainty-aware blind image quality assessment in the laboratory and wild' and 'Learning to blindly assess image quality in the laboratory and wild'

Official repository for MaPLe-IQA

Fast Adversarial CNN-based Perturbation Attack on no-reference image- and video-quality metrics

Non-local Modeling for Image Quality Assessment

Universal Perturbation Attack on differentiable no-reference image- and video-quality metrics

[official] No reference image quality assessment based Semantic Feature Aggregation, published in ACM MM 2017, TMM 2019

ACM MM 2019 SGDNet: An End-to-End Saliency-Guided Deep Neural Network for No-Reference Image Quality Assessment

[unofficial] Pytorch implementation of WaDIQaM in TIP2018, Bosse S. et al. (Deep neural networks for no-reference and full-reference image quality assessment)

[unofficial] CVPR2014-Convolutional neural networks for no-reference image quality assessment

[unofficial] PyTorch Implementation of image quality assessment methods: IQA-CNN++ in ICIP2015 and IQA-CNN in CVPR2014

Cause the original CEIQ code is written in MATLAB, it is difficult to integrate the model into python codes. This CEIQ model is trained on kadid10k dataset, which contains only 220 images vs 1500+ used in the original model. Therefore, the results may different and not so accurately compared to the original model.