The CelebA-HQ dataset is a high-quality version of CelebA that consists of 30,000 images at 1024×1024 resolution.
393 PAPERS • 11 BENCHMARKS
Includes more than two million traffic sign images that are based on real-world and simulator data.
9 PAPERS • NO BENCHMARKS YET
TID2013 is a dataset for image quality assessment that contains 25 reference images and 3000 distorted images (25 reference images x 24 types of distortions x 5 levels of distortions).
3 PAPERS • NO BENCHMARKS YET
Dataset with 28,792 retinal images from the EyePACS dataset, based on a three-level quality grading system (i.e., Good',Usable' and `Reject') for evaluating RIQA methods.
2 PAPERS • NO BENCHMARKS YET
Cross-Reference Omnidirectional Stitching IQA is a novel omnidirectional image dataset containing stitched images as well as dual-fisheye images captured from standard quarters of 0◦, 90◦ , 180◦ and 270◦. In this manner, when evaluating the quality of an image stitched from a pair of fisheye images (e.g., 0◦ and 180◦), the other pair of fisheye images (e.g., 90◦ and 270◦) can be used as the cross-reference to provide ground-truth observations of the stitching regions.
1 PAPER • NO BENCHMARKS YET