{"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/self-supervised-generation-of-spatial-audio-1","title":"Self-Supervised Generation of Spatial Audio for 360 Video","arxiv_id":"1809.02587","date":"2018-09-07","proceeding":null,"authors":["Pedro Morgado","Nuno Vasconcelos","Timothy Langlois","Oliver Wang"],"abstract":"We introduce an approach to convert mono audio recorded by a 360 video camera\ninto spatial audio, a representation of the distribution of sound over the full\nviewing sphere. Spatial audio is an important component of immersive 360 video\nviewing, but spatial audio microphones are still rare in current 360 video\nproduction. Our system consists of end-to-end trainable neural networks that\nseparate individual sound sources and localize them on the viewing sphere,\nconditioned on multi-modal analysis of audio and 360 video frames. We introduce\nseveral datasets, including one filmed ourselves, and one collected in-the-wild\nfrom YouTube, consisting of 360 videos uploaded with spatial audio. During\ntraining, ground-truth spatial audio serves as self-supervision and a mixed\ndown mono track forms the input to our network. Using our approach, we show\nthat it is possible to infer the spatial location of sound sources based only\non 360 video and a mono audio track.","url_abs":"http://arxiv.org/abs/1809.02587v1","url_pdf":"http://arxiv.org/pdf/1809.02587v1.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":"self-supervised-generation-of-spatial-audio-1","repo_url":"https://github.com/pedro-morgado/spatialaudiogen","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1809.02587","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}