[CVPRW oral 2022] MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment
Pytorch version of IEEE Transactions on Multimedia 2019: "Naturalness-Aware Deep No-Reference Image Quality Assessment."
Pytorch version of the CVPR2014 paper: "Deep CNN-Based Blind Image Quality Predictor."
Pytorch version of IEEE Transactions on Image Processing 2019 : "Two-Stream Convolutional Networks for Blind Image Quality Assessment"
Content-variant reference IQA via knowledge distillation: a full-reference teacher transfers high-quality distribution priors to a student that needs only a non-pixel-aligned / content-variant reference, so quality scores no longer require a pixel-perfect reference image.
Structure-Preserving Nonlinear Sufficient Dimension Reduction
Conditional Knowledge Distillation Network (CKDN) for blind image quality assessment of restored images using a degraded reference (PyTorch, ResNet-50 two-branch: QSE + DTE). Trained/evaluated on CSIQ and TID2013 with SRCC/PLCC metrics.
To associate your repository with the csiq topic, visit your repo's landing page and select "manage topics."