{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/image-quality-assessment-for-omnidirectional","title":"Image Quality Assessment for Omnidirectional Cross-reference Stitching","arxiv_id":"1904.04960","date":"2019-04-10","proceeding":null,"authors":["Kaiwen Yu","Jia Li","Yu Zhang","Yifan Zhao","Long Xu"],"abstract":"Along with the development of virtual reality (VR), omnidirectional images\nplay an important role in producing multimedia content with immersive\nexperience. However, despite various existing approaches for omnidirectional\nimage stitching, how to quantitatively assess the quality of stitched images is\nstill insufficiently explored. To address this problem, we establish a novel\nomnidirectional image dataset containing stitched images as well as\ndual-fisheye images captured from standard quarters of 0$^\\circ$, 90$^\\circ$,\n180$^\\circ$ and 270$^\\circ$. In this manner, when evaluating the quality of an\nimage stitched from a pair of fisheye images (e.g., 0$^\\circ$ and 180$^\\circ$),\nthe other pair of fisheye images (e.g., 90$^\\circ$ and 270$^\\circ$) can be used\nas the cross-reference to provide ground-truth observations of the stitching\nregions. Based on this dataset, we further benchmark six widely used stitching\nmodels with seven evaluation metrics for IQA. To the best of our knowledge, it\nis the first dataset that focuses on assessing the stitching quality of\nomnidirectional images.","url_abs":"http://arxiv.org/abs/1904.04960v2","url_pdf":"http://arxiv.org/pdf/1904.04960v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"image-quality-assessment","task_name":"Image Quality Assessment"},{"task_slug":"image-stitching","task_name":"Image Stitching"}],"methods":[],"datasets_introduced":[{"slug":"cross","name":"CROSS","full_name":"Cross-Reference Omnidirectional Stitching IQA"}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}