{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T12:00:55Z","timestamp":1780056055891,"version":"3.54.0"},"publisher-location":"New York, NY, USA","reference-count":73,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,9,28]]},"DOI":"10.1145\/3746059.3747730","type":"proceedings-article","created":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T07:49:12Z","timestamp":1758959352000},"page":"1-16","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Enhancing XR Auditory Realism via Multimodal Scene-Aware Acoustic Rendering"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-9135-6080","authenticated-orcid":false,"given":"Tianyu","family":"Xu","sequence":"first","affiliation":[{"name":"Google, Mountain View, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1696-5738","authenticated-orcid":false,"given":"Jihan","family":"Li","sequence":"additional","affiliation":[{"name":"Google, Mountain View, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8623-9229","authenticated-orcid":false,"given":"Penghe","family":"Zu","sequence":"additional","affiliation":[{"name":"Google, Mountain View, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1887-3961","authenticated-orcid":false,"given":"Pranav","family":"Sahay","sequence":"additional","affiliation":[{"name":"Google, Mountain View, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7032-4682","authenticated-orcid":false,"given":"Maruchi","family":"Kim","sequence":"additional","affiliation":[{"name":"Google, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0359-1010","authenticated-orcid":false,"given":"Jack","family":"Obeng-Marnu","sequence":"additional","affiliation":[{"name":"Google, San Francisco, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5845-8407","authenticated-orcid":false,"given":"Farley","family":"Miller","sequence":"additional","affiliation":[{"name":"Cognizant, Mountain View, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1976-7992","authenticated-orcid":false,"given":"Xun","family":"Qian","sequence":"additional","affiliation":[{"name":"Google, Mountain View, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8670-1833","authenticated-orcid":false,"given":"Katrina","family":"Passarella","sequence":"additional","affiliation":[{"name":"Google, San Francisco, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1286-1241","authenticated-orcid":false,"given":"Mahitha","family":"Rachumalla","sequence":"additional","affiliation":[{"name":"Google, Mountain View, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1834-1758","authenticated-orcid":false,"given":"Rajeev","family":"Nongpiur","sequence":"additional","affiliation":[{"name":"Google, Mountain View, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7133-292X","authenticated-orcid":false,"given":"D","family":"Shin","sequence":"additional","affiliation":[{"name":"Google, Mountain View, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,9,27]]},"reference":[{"key":"e_1_3_3_1_2_2","unstructured":"2009. Acoustics \u2013 Measurement of Room Acoustic Parameters \u2013 Part 1: Performance Spaces. https:\/\/www.iso.org\/obp\/ui\/es\/#iso:std:iso:3382:-1:ed-1:v1:en"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","unstructured":"Jont\u00a0B. Allen and David\u00a0A. Berkley. 1979. Image Method for Efficiently Simulating Small-Room Acoustics. The Journal of the Acoustical Society of America 65 4 (04 1979) 943\u2013950. 10.1121\/1.382599","DOI":"10.1121\/1.382599"},{"key":"e_1_3_3_1_4_2","unstructured":"Apple Inc.2024. Apple Vision Pro - Technical Specifications. https:\/\/www.apple.com\/apple-vision-pro\/specs\/. Accessed: April 4 2025."},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","unstructured":"Ronald\u00a0T. Azuma. 1997. A Survey of Augmented Reality. Presence: Teleoperators and Virtual Environments 6 4 (08 1997) 355\u2013385. 10.1162\/pres.1997.6.4.355 arXiv:https:\/\/direct.mit.edu\/pvar\/article-pdf\/6\/4\/355\/1623026\/pres.1997.6.4.355.pdf","DOI":"10.1162\/pres.1997.6.4.355"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00193"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01804"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","unstructured":"Mark Billinghurst Adrian Clark and Gun Lee. 2015. A Survey of Augmented Reality. Foundations and Trends in Human\u2013Computer Interaction 8 2-3 (2015) 73\u2013272. 10.1561\/1100000049","DOI":"10.1561\/1100000049"},{"key":"e_1_3_3_1_9_2","volume-title":"Spatial Hearing: The Psychophysics of Human Sound Localization","author":"Blauert Jens","year":"1997","unstructured":"Jens Blauert. 1997. Spatial Hearing: The Psychophysics of Human Sound Localization. MIT Press, Cambridge, MA."},{"key":"e_1_3_3_1_10_2","unstructured":"Jessica\u00a0Y. Bo Tianyu Xu Ishan Chatterjee Katrina Passarella-Ward Achin Kulshrestha and D Shin. 2025. Steerable Chatbots: Personalizing LLMs with Preference-Based Activation Steering. arxiv:https:\/\/arXiv.org\/abs\/2505.04260\u00a0[cs.HC] https:\/\/arxiv.org\/abs\/2505.04260"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"crossref","unstructured":"Zal\u00e1n Borsos Rapha\u00ebl Marinier Damien Vincent Eugene Kharitonov Olivier Pietquin Matt Sharifi Dominik Roblek Olivier Teboul David Grangier Marco Tagliasacchi and Neil Zeghidour. 2023. AudioLM: a Language Modeling Approach to Audio Generation. arxiv:https:\/\/arXiv.org\/abs\/2209.03143\u00a0[cs.SD] https:\/\/arxiv.org\/abs\/2209.03143","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","unstructured":"Virginia Braun and Victoria Clarke. 2006. Using Thematic Analysis in Psychology. Qualitative Research in Psychology 3 2 (2006) 77\u2013101. 10.1191\/1478088706qp063oa","DOI":"10.1191\/1478088706qp063oa"},{"key":"e_1_3_3_1_13_2","volume-title":"The Boundary Element Method for Engineers","author":"Brebbia C.\u00a0A.","year":"1978","unstructured":"C.\u00a0A. Brebbia. 1978. The Boundary Element Method for Engineers. Pentech Press."},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.6821775"},{"key":"e_1_3_3_1_15_2","unstructured":"Holger Caesar Jasper Uijlings and Vittorio Ferrari. 2018. COCO-Stuff: Thing and Stuff Classes in Context. arxiv:https:\/\/arXiv.org\/abs\/1612.03716\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/1612.03716"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3498361.3538933"},{"key":"e_1_3_3_1_17_2","unstructured":"Liang-Chieh Chen George Papandreou Florian Schroff and Hartwig Adam. 2017. Rethinking Atrous Convolution for Semantic Image Segmentation. arxiv:https:\/\/arXiv.org\/abs\/1706.05587\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/1706.05587"},{"key":"e_1_3_3_1_18_2","unstructured":"Liang-Chieh Chen Yukun Zhu George Papandreou Florian Schroff and Hartwig Adam. 2018. Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation. arxiv:https:\/\/arXiv.org\/abs\/1802.02611\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/1802.02611"},{"key":"e_1_3_3_1_19_2","unstructured":"Yi\u00a0Fei Cheng Ari Carden Hyunsung Cho Catarina\u00a0G. Fidalgo Jonathan Wieland and David Lindlbauer. 2025. Augmented Reality In-the-Wild: Usage Patterns and Experiences of Working with AR Laptops in Real-World Settings. arxiv:https:\/\/arXiv.org\/abs\/2502.14241\u00a0[cs.HC] https:\/\/arxiv.org\/abs\/2502.14241"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3654777.3676424"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/CoG51982.2022.9893613"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","unstructured":"Abe Davis* Katherine\u00a0L. Bouman* Justin\u00a0G. Chen Michael Rubinstein Oral B\u00fcy\u00fck\u00f6zt\u00fcrk Fr\u00e9do Durand and William\u00a0T. Freeman. 2017. Visual Vibrometry: Estimating Material Properties from Small Motions in Video. IEEE Transactions on Pattern Analysis and Machine Intelligence 39 4 (2017) 732\u2013745. 10.1109\/TPAMI.2016.2622271","DOI":"10.1109\/TPAMI.2016.2622271"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3654777.3676379"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3379337.3415881"},{"key":"e_1_3_3_1_26_2","unstructured":"Alexandre D\u00e9fossez Jade Copet Gabriel Synnaeve and Yossi Adi. 2022. High Fidelity Neural Audio Compression. arxiv:https:\/\/arXiv.org\/abs\/2210.13438\u00a0[eess.AS] https:\/\/arxiv.org\/abs\/2210.13438"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","unstructured":"C.\u00a0F. Eyring. 1930. Reverberation time in \u201cdead\u201d rooms. The Journal of the Acoustical Society of America 1 2a (1930) 217\u2013241. 10.1121\/1.1915175","DOI":"10.1121\/1.1915175"},{"key":"e_1_3_3_1_28_2","volume-title":"Audio Engineering Society Convention 108","author":"Farina Angelo","year":"2000","unstructured":"Angelo Farina. 2000. Simultaneous measurement of impulse response and distortion with a swept-sine technique. In Audio Engineering Society Convention 108."},{"key":"e_1_3_3_1_29_2","unstructured":"Google. 2024. Gemini. https:\/\/deepmind.google\/technologies\/gemini\/ Large language model developed by Google."},{"key":"e_1_3_3_1_30_2","unstructured":"Google. 2025. Google Gemini Pro 2.5 (Experimental Version). https:\/\/gemini.google.com\/. [Large language model Experimental Version]. Accessed: 2025-04-08."},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.17743\/aesconf.2019.978-1-942220-22-5"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/VRAIS.1995.512482"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","unstructured":"Claudia Hendrix and Woodrow Barfield. 1996. The Sense of Presence within Auditory Virtual Environments. Presence: Teleoperators and Virtual Environments 5 3 (08 1996) 290\u2013301. 10.1162\/pres.1996.5.3.290","DOI":"10.1162\/pres.1996.5.3.290"},{"key":"e_1_3_3_1_34_2","unstructured":"Geoffrey Hinton. 2012. Neural Networks for Machine Learning Lecture 6a: RMSprop. Coursera course notes. http:\/\/www.cs.toronto.edu\/\u00a0tijmen\/csc321\/slides\/lecture_slides_lec6.pdf"},{"key":"e_1_3_3_1_35_2","volume-title":"Method for the subjective assessment of intermediate quality level of coding systems","author":"(ITU) International Telecommunication Union","year":"2003","unstructured":"International Telecommunication Union (ITU). 2003. Method for the subjective assessment of intermediate quality level of coding systems. Recommendation BS.1534-1. Radiocommunication Sector (ITU-R). Recommendation ITU-R BS.1534-1 (Superseded by BS.1534-3)."},{"key":"e_1_3_3_1_36_2","volume-title":"Method for the Subjective Assessment of Intermediate Quality Level of Audio Systems","author":"(ITU) International Telecommunication Union","year":"2015","unstructured":"International Telecommunication Union (ITU). 2015. Method for the Subjective Assessment of Intermediate Quality Level of Audio Systems. Recommendation BS.1534-3. Radiocommunication Sector (ITU-R). Recommendation ITU-R BS.1534-3."},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/2792790.2792830"},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.226080"},{"key":"e_1_3_3_1_39_2","volume-title":"Audio Engineering Society Convention 90","author":"Jot Jean-Marc","year":"1991","unstructured":"Jean-Marc Jot and Antoine Chaigne. 1991. Digital delay networks for designing artificial reverberators. In Audio Engineering Society Convention 90."},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.5555\/3019350"},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/VR.2019.8798247"},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"crossref","unstructured":"Alexander Kirillov Eric Mintun Nikhila Ravi Hanzi Mao Chloe Rolland Laura Gustafson Tete Xiao Spencer Whitehead Alexander\u00a0C. Berg Wan-Yen Lo Piotr Doll\u00e1r and Ross Girshick. 2023. Segment Anything. arxiv:https:\/\/arXiv.org\/abs\/2304.02643\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2304.02643","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1201\/9781315372150"},{"key":"e_1_3_3_1_44_2","unstructured":"Zitong Lan Chenhao Zheng Zhiwei Zheng and Mingmin Zhao. 2024. Acoustic Volume Rendering for Neural Impulse Response Fields. arxiv:https:\/\/arXiv.org\/abs\/2411.06307\u00a0[cs.SD] https:\/\/arxiv.org\/abs\/2411.06307"},{"key":"e_1_3_3_1_45_2","unstructured":"Lik-Hang Lee Tristan Braud Pengyuan Zhou Lin Wang Dianlei Xu Zijun Lin Abhishek Kumar Carlos Bermejo and Pan Hui. 2021. All One Needs to Know about Metaverse: A Complete Survey on Technological Singularity Virtual Ecosystem and Research Agenda. arxiv:https:\/\/arXiv.org\/abs\/2110.05352\u00a0[cs.CY] https:\/\/arxiv.org\/abs\/2110.05352"},{"key":"e_1_3_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445532"},{"key":"e_1_3_3_1_47_2","doi-asserted-by":"publisher","unstructured":"Alexander Lindau and Stefan Weinzierl. 2012. Assessing the Plausibility of Virtual Acoustic Environments. Acta Acustica united with Acustica 98 (09 2012) 804\u2013810. 10.3813\/AAA.918562","DOI":"10.3813\/AAA.918562"},{"key":"e_1_3_3_1_48_2","doi-asserted-by":"crossref","unstructured":"Chen Liu Kihwan Kim Jinwei Gu Yasutaka Furukawa and Jan Kautz. 2019. PlaneRCNN: 3D Plane Detection and Reconstruction from a Single Image. arxiv:https:\/\/arXiv.org\/abs\/1812.04072\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/1812.04072","DOI":"10.1109\/CVPR.2019.00458"},{"key":"e_1_3_3_1_49_2","unstructured":"Chen Liu Jimei Yang Duygu Ceylan Ersin Yumer and Yasutaka Furukawa. 2018. PlaneNet: Piece-wise Planar Reconstruction from a Single RGB Image. arxiv:https:\/\/arXiv.org\/abs\/1804.06278\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/1804.06278"},{"key":"e_1_3_3_1_50_2","unstructured":"Andrew Luo Yilun Du Michael\u00a0J. Tarr Joshua\u00a0B. Tenenbaum Antonio Torralba and Chuang Gan. 2023. Learning Neural Acoustic Fields. arxiv:https:\/\/arXiv.org\/abs\/2204.00628\u00a0[cs.SD] https:\/\/arxiv.org\/abs\/2204.00628"},{"key":"e_1_3_3_1_51_2","unstructured":"Paul Milgram and Fumio Kishino. 1994. A Taxonomy of Mixed Reality Visual Displays. IEICE Transactions on Information and Systems 77 (1994) 1321\u20131329. https:\/\/api.semanticscholar.org\/CorpusID:17783728"},{"key":"e_1_3_3_1_52_2","doi-asserted-by":"publisher","unstructured":"Ra\u00fal Mur-Artal J.\u00a0M.\u00a0M. Montiel and Juan\u00a0D. Tard\u00f3s. 2015. ORB-SLAM: A Versatile and Accurate Monocular SLAM System. IEEE Transactions on Robotics 31 5 (2015) 1147\u20131163. 10.1109\/TRO.2015.2463671","DOI":"10.1109\/TRO.2015.2463671"},{"key":"e_1_3_3_1_53_2","doi-asserted-by":"crossref","unstructured":"Michael Niemeyer Fabian Manhardt Marie-Julie Rakotosaona Michael Oechsle Daniel Duckworth Rama Gosula Keisuke Tateno John Bates Dominik Kaeser and Federico Tombari. 2025. RadSplat: Radiance Field-Informed Gaussian Splatting for Robust Real-Time Rendering with 900+ FPS. arxiv:https:\/\/arXiv.org\/abs\/2403.13806\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2403.13806","DOI":"10.1109\/3DV66043.2025.00018"},{"key":"e_1_3_3_1_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/2984511.2984517"},{"key":"e_1_3_3_1_55_2","doi-asserted-by":"crossref","unstructured":"Songyou Peng Kyle Genova Chiyu\u00a0\"Max\" Jiang Andrea Tagliasacchi Marc Pollefeys and Thomas Funkhouser. 2023. OpenScene: 3D Scene Understanding with Open Vocabularies. arxiv:https:\/\/arXiv.org\/abs\/2211.15654\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2211.15654","DOI":"10.1109\/CVPR52729.2023.00085"},{"key":"e_1_3_3_1_56_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642110"},{"key":"e_1_3_3_1_57_2","volume-title":"Snapdragon XR2+ Gen 2 Platform Product Brief","author":"Inc. Qualcomm Technologies,","year":"2024","unstructured":"Qualcomm Technologies, Inc.2024. Snapdragon XR2+ Gen 2 Platform Product Brief. Product Brief 87-73622-1 Rev. A. Qualcomm Technologies, Inc.https:\/\/docs.qualcomm.com\/bundle\/publicresource\/87-73622-1_REV_A_Snapdragon_XR2__Gen_2_Platform_Product_Brief.pdf"},{"key":"e_1_3_3_1_58_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02565"},{"key":"e_1_3_3_1_59_2","doi-asserted-by":"publisher","DOI":"10.1145\/1358628.1358969"},{"key":"e_1_3_3_1_60_2","unstructured":"Francis Rumsey. 2002. Spatial quality evaluation for reproduced sound: Terminology meaning and methods. Journal of the Audio Engineering Society 50 9 (September 2002) 651\u2013666."},{"key":"e_1_3_3_1_61_2","unstructured":"Mark Sandler Andrew Howard Menglong Zhu Andrey Zhmoginov and Liang-Chieh Chen. 2019. MobileNetV2: Inverted Residuals and Linear Bottlenecks. arxiv:https:\/\/arXiv.org\/abs\/1801.04381\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/1801.04381"},{"key":"e_1_3_3_1_62_2","unstructured":"Manfred\u00a0R. Schroeder. 1962. Natural Sounding Artificial Reverberation. Journal of the Audio Engineering Society 10 3 (1962) 219\u2013223."},{"key":"e_1_3_3_1_63_2","first-page":"531","volume-title":"Handbook of Virtual Environments: Design, Implementation, and Applications (second ed.)","author":"Serafin Stefania","year":"2016","unstructured":"Stefania Serafin, Cumhur Erkut, Juraj Kojs, Niels\u00a0C. Nilsson, and Rolf Nordahl. 2016. Auditory feedback. In Handbook of Virtual Environments: Design, Implementation, and Applications (second ed.), Kelly\u00a0S. Hale and Kay\u00a0M. Stanney (Eds.). CRC Press, Boca Raton, FL, 531\u2013556."},{"key":"e_1_3_3_1_64_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00035"},{"key":"e_1_3_3_1_65_2","doi-asserted-by":"publisher","unstructured":"Jonathan Steuer. 1992. Defining Virtual Reality: Dimensions Determining Telepresence. Journal of Communication 42 4 (1992) 73\u201393. 10.1111\/j.1460-2466.1992.tb00812.x","DOI":"10.1111\/j.1460-2466.1992.tb00812.x"},{"key":"e_1_3_3_1_66_2","unstructured":"The Khronos Group. [n. d.]. OpenXR\u2122 API Specification. https:\/\/www.khronos.org\/openxr\/. Accessed: 2025-04-10."},{"key":"e_1_3_3_1_67_2","doi-asserted-by":"publisher","unstructured":"Guansen Tong Johnathan Chi-Ho Leung Xi Peng Haosheng Shi Liujie Zheng Shengze Wang Arryn\u00a0Carlos O\u2019Brien Ashley Paula-Ann Neall Grace Fei Martim Gaspar and Praneeth Chakravarthula. 2025. Multimodal Neural Acoustic Fields for Immersive Mixed Reality. IEEE Transactions on Visualization and Computer Graphics (2025) 1\u201311. 10.1109\/TVCG.2025.3549898","DOI":"10.1109\/TVCG.2025.3549898"},{"key":"e_1_3_3_1_68_2","doi-asserted-by":"publisher","DOI":"10.1145\/383259.383323"},{"key":"e_1_3_3_1_69_2","doi-asserted-by":"publisher","unstructured":"Tianyi Wang Xun Qian Fengming He Xiyun Hu Yuanzhi Cao and Karthik Ramani. 2021. GesturAR: An Authoring System for Creating Freehand Interactive Augmented Reality Applications(UIST \u201921). Association for Computing Machinery New York NY USA 552\u2013567. 10.1145\/3472749.3474769","DOI":"10.1145\/3472749.3474769"},{"key":"e_1_3_3_1_70_2","doi-asserted-by":"publisher","unstructured":"Elizabeth\u00a0M. Wenzel Marianne Arruda Doris\u00a0J. Kistler and Frederic\u00a0L. Wightman. 1993. Localization using nonindividualized head-related transfer functions. The Journal of the Acoustical Society of America 94 1 (07 1993) 111\u2013123. 10.1121\/1.407089","DOI":"10.1121\/1.407089"},{"key":"e_1_3_3_1_71_2","doi-asserted-by":"publisher","unstructured":"Kane\u00a0S. Yee. 1966. Numerical Solution of Initial Boundary Value Problems Involving Maxwell\u2019s Equations in Isotropic Media. IEEE Transactions on Antennas and Propagation 14 3 (1966) 302\u2013307. 10.1109\/TAP.1966.1138693","DOI":"10.1109\/TAP.1966.1138693"},{"key":"e_1_3_3_1_72_2","unstructured":"Neil Zeghidour Alejandro Luebs Ahmed Omran Jan Skoglund and Marco Tagliasacchi. 2021. SoundStream: An End-to-End Neural Audio Codec. arxiv:https:\/\/arXiv.org\/abs\/2107.03312\u00a0[cs.SD] https:\/\/arxiv.org\/abs\/2107.03312"},{"key":"e_1_3_3_1_73_2","unstructured":"Richard Zhang Phillip Isola and Alexei\u00a0A. Efros. 2016. Colorful Image Colorization. arxiv:https:\/\/arXiv.org\/abs\/1603.08511\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/1603.08511"},{"key":"e_1_3_3_1_74_2","doi-asserted-by":"publisher","DOI":"10.1145\/3526113.3545705"}],"event":{"name":"UIST '25: The 38th Annual ACM Symposium on User Interface Software and Technology","location":"Busan Republic of Korea","acronym":"UIST '25","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction","SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Proceedings of the 38th Annual ACM Symposium on User Interface Software and Technology"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746059.3747730","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T22:13:41Z","timestamp":1759011221000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746059.3747730"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,27]]},"references-count":73,"alternative-id":["10.1145\/3746059.3747730","10.1145\/3746059"],"URL":"https:\/\/doi.org\/10.1145\/3746059.3747730","relation":{},"subject":[],"published":{"date-parts":[[2025,9,27]]},"assertion":[{"value":"2025-09-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}