Implementation of technical image quality model based on Google's research paper "NIMA: Neural Image Assessment".
-
Updated
Mar 10, 2019 - Python
#
tid2013
Here are 4 public repositories matching this topic...
An implementation of the NIMA paper on the TID2013 dataset, using PyTorch.
-
Updated
Mar 23, 2020 - Python
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.
computer-vision deep-learning pytorch resnet knowledge-distillation ntire image-quality-assessment tid2013 full-reference-iqa csiq kadid10k mlp-mixer no-reference-iqa live-challenge koniq10k
-
Updated
Sep 6, 2026 - Python
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.
computer-vision deep-learning pytorch resnet knowledge-distillation image-restoration iqa image-quality-assessment blind-image-quality-assessment tid2013 csiq no-reference-image-quality-assessment degraded-reference-iqa
-
Updated
Sep 4, 2026 - Python
Add this topic to your repo
To associate your repository with the tid2013 topic, visit your repo's landing page and select "manage topics."