{"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/towards-a-quality-metric-for-dense-light","title":"Towards a quality metric for dense light fields","arxiv_id":"1704.07576","date":"2017-04-25","proceeding":"CVPR 2017 7","authors":["Vamsi Kiran Adhikarla","Marek Vinkler","Denis Sumin","Rafał K. Mantiuk","Karol Myszkowski","Hans-Peter Seidel","Piotr Didyk"],"abstract":"Light fields become a popular representation of three dimensional scenes, and\nthere is interest in their processing, resampling, and compression. As those\noperations often result in loss of quality, there is a need to quantify it. In\nthis work, we collect a new dataset of dense reference and distorted light\nfields as well as the corresponding quality scores which are scaled in\nperceptual units. The scores were acquired in a subjective experiment using an\ninteractive light-field viewing setup. The dataset contains typical artifacts\nthat occur in light-field processing chain due to light-field reconstruction,\nmulti-view compression, and limitations of automultiscopic displays. We test a\nnumber of existing objective quality metrics to determine how well they can\npredict the quality of light fields. We find that the existing image quality\nmetrics provide good measures of light-field quality, but require dense\nreference light- fields for optimal performance. For more complex tasks of\ncomparing two distorted light fields, their performance drops significantly,\nwhich reveals the need for new, light-field-specific metrics.","url_abs":"http://arxiv.org/abs/1704.07576v1","url_pdf":"http://arxiv.org/pdf/1704.07576v1.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":[{"paper_slug":"towards-a-quality-metric-for-dense-light","repo_url":"https://github.com/mantiuk/pwcmp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1704.07576","atlas_url":"https://app.syntology.ai/?focus=1704.07576","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}