Multimodal Neural Acoustic Fields for Immersive Mixed Reality

We introduce multimodal neural acoustic fields for synthesizing spatial sound and enabling the creation of immersive auditory experiences from novel viewpoints and in completely unseen new environments, both virtual and real. Extending the concept of neural radiance fields to acoustics, we develop a...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on visualization and computer graphics. - 1996. - 31(2025), 5 vom: 01. Mai, Seite 3397-3407
1. Verfasser: Tong, Guaneen (VerfasserIn)
Weitere Verfasser: Leung, Johnathan Chi-Ho, Peng, Xi, Shi, Haosheng, Zheng, Liujie, Wang, Shengze, O'Brien, Arryn Carlos, Neall, Ashley Paula-Ann, Fei, Grace, Gaspar, Martim, Chakravarthula, Praneeth
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2025
Zugriff auf das übergeordnete Werk:IEEE transactions on visualization and computer graphics
Schlagworte:Journal Article
LEADER 01000caa a22002652c 4500
001 NLM38619341X
003 DE-627
005 20250509152112.0
007 cr uuu---uuuuu
008 250508s2025 xx |||||o 00| ||eng c
024 7 |a 10.1109/TVCG.2025.3549898  |2 doi 
028 5 2 |a pubmed25n1386.xml 
035 |a (DE-627)NLM38619341X 
035 |a (NLM)40138240 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Tong, Guaneen  |e verfasserin  |4 aut 
245 1 0 |a Multimodal Neural Acoustic Fields for Immersive Mixed Reality 
264 1 |c 2025 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Revised 25.04.2025 
500 |a published: Print-Electronic 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a We introduce multimodal neural acoustic fields for synthesizing spatial sound and enabling the creation of immersive auditory experiences from novel viewpoints and in completely unseen new environments, both virtual and real. Extending the concept of neural radiance fields to acoustics, we develop a neural network-based model that maps an environment's geometric and visual features to its audio characteristics. Specifically, we introduce a novel hybrid transformer-convolutional neural network to accomplish two core tasks: capturing the reverberation characteristics of a scene from audio-visual data, and generating spatial sound in an unseen new environment from signals recorded at sparse positions and orientations within the original scene. By learning to represent spatial acoustics in a given environment, our approach enables creation of realistic immersive auditory experiences, thereby enhancing the sense of presence in augmented and virtual reality applications. We validate the proposed approach on both synthetic and real-world visual-acoustic data and demonstrate that our method produces nonlinear acoustic effects such as reverberations, and improves spatial audio quality compared to existing methods. Furthermore, we also conduct subjective user studies and demonstrate that the proposed framework significantly improves audio perception in immersive mixed reality applications 
650 4 |a Journal Article 
700 1 |a Leung, Johnathan Chi-Ho  |e verfasserin  |4 aut 
700 1 |a Peng, Xi  |e verfasserin  |4 aut 
700 1 |a Shi, Haosheng  |e verfasserin  |4 aut 
700 1 |a Zheng, Liujie  |e verfasserin  |4 aut 
700 1 |a Wang, Shengze  |e verfasserin  |4 aut 
700 1 |a O'Brien, Arryn Carlos  |e verfasserin  |4 aut 
700 1 |a Neall, Ashley Paula-Ann  |e verfasserin  |4 aut 
700 1 |a Fei, Grace  |e verfasserin  |4 aut 
700 1 |a Gaspar, Martim  |e verfasserin  |4 aut 
700 1 |a Chakravarthula, Praneeth  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on visualization and computer graphics  |d 1996  |g 31(2025), 5 vom: 01. Mai, Seite 3397-3407  |w (DE-627)NLM098269445  |x 1941-0506  |7 nnas 
773 1 8 |g volume:31  |g year:2025  |g number:5  |g day:01  |g month:05  |g pages:3397-3407 
856 4 0 |u http://dx.doi.org/10.1109/TVCG.2025.3549898  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 31  |j 2025  |e 5  |b 01  |c 05  |h 3397-3407