CROSS
Cross-Reference Omnidirectional Stitching IQA
ImagesIntroduced 2019-04-10
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.
Source: Image Quality Assessment for Omnidirectional Cross-reference Stitching
Related Benchmarks
Cross-View Time Dataset/Image Classification/2-Class AccuracyCross-View Time Dataset/Image Classification/AUCCross-View Time Dataset (Cross-Camera Split)/Image Classification/2-Class AccuracyCross-View Time Dataset (Cross-Camera Split)/Image Classification/AUCCrossNER/Named Entity Recognition (NER)/AICrossNER/Named Entity Recognition (NER)/LiteratureCrossNER/Named Entity Recognition (NER)/MusicCrossNER/Named Entity Recognition (NER)/PoliticsCrossNER/Named Entity Recognition (NER)/ScienceCrossTask/Action Localization/RecallCrossTask/Temporal Action Localization/RecallCrossTask/Video/RecallCrossTask/Zero-Shot Learning/Recall