{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:30:45Z","timestamp":1777865445931,"version":"3.51.4"},"reference-count":52,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01294","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"13942-13951","source":"Crossref","is-referenced-by-count":0,"title":["$\\pi$-AVAS: Can Physics-Integrated Audio-Visual Modeling Boost Neural Acoustic Synthesis?"],"prefix":"10.1109","author":[{"given":"Susan","family":"Liang","sequence":"first","affiliation":[{"name":"University of Rochester"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Rochester"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunlong","family":"Tang","sequence":"additional","affiliation":[{"name":"University of Rochester"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zeliang","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Rochester"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenliang","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Rochester"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0910"},{"key":"ref2","article-title":"Neraf: 3d scene infused neural radiance and acoustic fields","author":"Brunetto","year":"2024","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2980179.2982431"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_2"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01829"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00620"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4477"},{"key":"ref8","first-page":"31","article-title":"Neural ordinary differential equations","author":"Chen","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02067"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.visres.2013.11.004"},{"key":"ref11","article-title":"Soaf: Scene occlusion-aware neural acoustic field","author":"Gao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00041"},{"key":"ref13","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72684-2_1"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02228"},{"key":"ref16","article-title":"Advanced audio coding (aac)","volume-title":"ISO\/IEC 13818\u20137","year":"2006"},{"key":"ref17","article-title":"Poisson surface reconstruction","volume-title":"Proceedings of the fourth Eurographics symposium on Geometry processing","author":"Kazhdan","year":"2006"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref19","article-title":"Introductory functional analysis with applications","author":"Kreyszig","year":"1991","journal-title":"John Wiley & Sons"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1417"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1629"},{"key":"ref22","article-title":"Neural acoustic context field: Rendering realistic room impulse response with neural fields","author":"Liang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-0960-4_8"},{"key":"ref24","article-title":"Binauralflow: A causal and streamable approach for high-quality binaural speech synthesis with flow matching models","author":"Liang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref25","article-title":"Flow matching for generative modeling","volume-title":"The Eleventh International Conference on Learning Representations","author":"Lipman"},{"key":"ref26","article-title":"Learning neural acoustic fields","author":"Luo","year":"2022","journal-title":"NeurIPS"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2121"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1006\/aima.1997.1634"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref30","article-title":"Self-supervised generation of spatial audio for 360 video","volume":"31","author":"Morgado","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref31","article-title":"A 3d ambisonic based binaural sound reproduction system","volume-title":"Audio Engineering Society Conference: 24th International Conference: Multichannel Audio, The New Reality","author":"Noisternig","year":"2003"},{"key":"ref32","article-title":"Movie gen: A cast of media foundation models","author":"Polyak","year":"2024","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02565"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73016-0_6"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1121\/1.4926438"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461310"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.445"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2907850"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1121\/1.2766781"},{"key":"ref41","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"International Conference on Learning Representations","author":"Song"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/960124.806879"},{"key":"ref43","article-title":"Inras: Implicit neural representation for audio scenes","author":"Su","year":"2022","journal-title":"NeurIPS"},{"key":"ref44","first-page":"7537","article-title":"Fourier features let networks learn high frequency functions in low dimensional domains","volume":"33","author":"Tancik","year":"2020","journal-title":"NeurIPS"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591516"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530731"},{"key":"ref47","article-title":"Improving and generalizing flow-based generative models with minibatch optimal transport","author":"Tong","journal-title":"Transactions on Machine Learning Research"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1609.03499"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref50","volume-title":"Xiph opus","year":"2012"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01523"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_35"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445353.pdf?arnumber=11445353","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:33:45Z","timestamp":1777530825000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445353\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01294","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}