{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T06:46:02Z","timestamp":1785653162791,"version":"3.56.0"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032316622","type":"print"},{"value":"9783032316639","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T00:00:00Z","timestamp":1785715200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T00:00:00Z","timestamp":1785715200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2027]]},"DOI":"10.1007\/978-3-032-31663-9_6","type":"book-chapter","created":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T05:48:27Z","timestamp":1785649707000},"page":"78-93","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SAVAF: Sparse Audio-Visual Rendering with\u00a0Multihead Acoustic Field Attention Network"],"prefix":"10.1007","author":[{"given":"Ahmed","family":"Hasssan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Meng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sungjin","family":"Park","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jae-sun","family":"Seo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,3]]},"reference":[{"key":"6_CR1","unstructured":"Aneja, S.: Gaussianspeech: Audio-driven gaussian avatars. arXiv preprint arXiv:2411.18675 (2024)"},{"key":"6_CR2","doi-asserted-by":"crossref","unstructured":"Bhosale, S.: Av-gs: Learning material and geometry aware priors for novel view acoustic synthesis (2024). arXiv preprint arXiv:2406.08920","DOI":"10.52202\/079017-0910"},{"key":"6_CR3","unstructured":"Brunetto, A.: Neraf: 3d scene infused neural radiance and acoustic fields. arXiv preprint arXiv:2405.18213 (2024)"},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Cadavid, J.: Spatial sampling versus acquisition time of room impulse responses for low-frequency sound zones. In: AES International Conference (2024)","DOI":"10.1121\/10.0023140"},{"key":"6_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1007\/978-3-030-58539-6_2","volume-title":"Computer Vision \u2013 ECCV 2020","author":"C Chen","year":"2020","unstructured":"Chen, C., Jain, U., Schissler, C., Gari, S.V.A., Al-Halah, Z., Ithapu, V.K., Robinson, P., Grauman, K.: SoundSpaces: Audio-Visual Navigation in\u00a03D\u00a0Environments. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12351, pp. 17\u201336. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58539-6_2"},{"key":"6_CR6","doi-asserted-by":"crossref","unstructured":"Chen, C.: Visual acoustic matching. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.01829"},{"key":"6_CR7","doi-asserted-by":"crossref","unstructured":"Chen, C.: Novel-view acoustic synthesis. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.00620"},{"key":"6_CR8","doi-asserted-by":"crossref","unstructured":"Chen, M.: Av-cloud: Spatial audio rendering through audio-visual cloud splatting. In: Advances in Neural Information Processing Systems (2024)","DOI":"10.52202\/079017-4477"},{"key":"6_CR9","doi-asserted-by":"crossref","unstructured":"Chen, Z.: Real acoustic fields: An audio-visual room acoustics dataset and benchmark. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, (2024)","DOI":"10.1109\/CVPR52733.2024.02067"},{"key":"6_CR10","doi-asserted-by":"crossref","unstructured":"Cho, K.: Gaussiantalker: Real-time talking head synthesis with 3d gaussian splatting. In: 32nd ACM International Conference on Multimedia (2024)","DOI":"10.1145\/3664647.3681627"},{"key":"6_CR11","unstructured":"Gao, H.: Soaf: Scene occlusion-aware neural acoustic field. arXiv preprint arXiv:2407.02264 (2024)"},{"key":"6_CR12","doi-asserted-by":"crossref","unstructured":"Gao, R.: 2.5 d visual sound. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00041"},{"key":"6_CR13","doi-asserted-by":"crossref","unstructured":"Garg, R.: Visually-guided audio spatialization in video with geometry-aware multi-task learning. Int. J. Comput. Vision (2023)","DOI":"10.1007\/s11263-023-01816-8"},{"key":"6_CR14","doi-asserted-by":"crossref","unstructured":"Guo, Y.: Ad-nerf: Audio driven neural radiance fields for talking head synthesis. In: International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.00573"},{"key":"6_CR15","doi-asserted-by":"crossref","unstructured":"Hasssan, A., et\u00a0al.: Quant-nerf: Efficient end-to-end quantization of neural radiance fields with low-precision 3d gaussian representation. In: ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE (2025)","DOI":"10.1109\/ICASSP49660.2025.10889510"},{"key":"6_CR16","doi-asserted-by":"crossref","unstructured":"Kerbl, B.: 3D gaussian splatting for real-time radiance field rendering. ACM Trans. Graph (4) (2023)","DOI":"10.1145\/3592433"},{"key":"6_CR17","doi-asserted-by":"crossref","unstructured":"Li, D.: Scene-aware audio for 360 videos. ACM Trans. Graph. (2018)","DOI":"10.1145\/3197517.3201391"},{"key":"6_CR18","doi-asserted-by":"crossref","unstructured":"Li, D.: Ae-nerf: Audio enhanced neural radiance field for few shot talking head synthesis. In: AAAI Conference on Artificial Intelligence (2024)","DOI":"10.1609\/aaai.v38i4.28086"},{"key":"6_CR19","doi-asserted-by":"crossref","unstructured":"Li, R.: Nerfacc: Efficient sampling accelerates nerfs. In: IEEE\/CVF International Conference on Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.01699"},{"key":"6_CR20","doi-asserted-by":"crossref","unstructured":"Liang, S.: Av-nerf: Learning neural fields for real-world audio-visual scene synthesis. In: Advances in Neural Information Processing Systems (2023)","DOI":"10.52202\/075280-1629"},{"key":"6_CR21","doi-asserted-by":"publisher","unstructured":"Liu, X.: Semantic-aware implicit neural audio-driven video portrait generation. In: European conference on computer vision. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19836-6_7","DOI":"10.1007\/978-3-031-19836-6_7"},{"key":"6_CR22","doi-asserted-by":"crossref","unstructured":"Luo, A.: Learning neural acoustic fields. In: Advances in Neural Information Processing Systems (2022)","DOI":"10.52202\/068431-0229"},{"key":"6_CR23","doi-asserted-by":"crossref","unstructured":"Martin-Brualla, R.: Nerf in the wild: Neural radiance fields for unconstrained photo collections. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.00713"},{"key":"6_CR24","doi-asserted-by":"crossref","unstructured":"Mildenhall, B.: Nerf: Representing scenes as neural radiance fields for view synthesis. Commun. ACM (1) (2021)","DOI":"10.1145\/3503250"},{"key":"6_CR25","doi-asserted-by":"crossref","unstructured":"Noda, K.: Audio-visual speech recognition using deep learning. Appl. Intell. (2015)","DOI":"10.1007\/s10489-014-0629-7"},{"key":"6_CR26","doi-asserted-by":"crossref","unstructured":"Rachavarapu, K.K.: Localize to binauralize: Audio spatialization from visual sound source localization. In: IEEE\/CVF International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.00194"},{"key":"6_CR27","doi-asserted-by":"crossref","unstructured":"Ratnarajah, A.: Av-rir: Audio-visual room impulse response estimation. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2024)","DOI":"10.1109\/CVPR52733.2024.02565"},{"key":"6_CR28","doi-asserted-by":"crossref","unstructured":"Schissler, C.: Acoustic classification and optimization for multi-modal rendering of real-world scenes. IEEE Trans. Visual Comput. Graphics (3) (2017)","DOI":"10.1109\/TVCG.2017.2666150"},{"key":"6_CR29","doi-asserted-by":"crossref","unstructured":"Schissler, C.: Fast diffraction pathfinding for dynamic sound propagation. ACM Trans. Graph. (4) (2021)","DOI":"10.1145\/3450626.3459751"},{"key":"6_CR30","doi-asserted-by":"crossref","unstructured":"Shin, A.H.: Wav2nerf: Audio-driven realistic talking head generation via wavelet-based nerf. Image Vis. Comput. (2024)","DOI":"10.2139\/ssrn.4643061"},{"key":"6_CR31","doi-asserted-by":"crossref","unstructured":"Su, K.: Inras: Implicit neural representation for audio scenes. In: Advances in Neural Information Processing Systems (2022)","DOI":"10.52202\/068431-0591"},{"key":"6_CR32","unstructured":"Usher, J.: Acoustic impulse response measurement using speech and music signals, Audio Engineering Society Convention 128. Audio Eng. Soc. (2010)"},{"key":"6_CR33","doi-asserted-by":"crossref","unstructured":"Xie, Y., et\u00a0al.: Pointtalk: Audio-driven dynamic lip point cloud for 3D gaussian-based talking head synthesis. In: AAAI Conference on Artificial Intelligence. No.\u00a08 (2025)","DOI":"10.1609\/aaai.v39i8.32946"},{"key":"6_CR34","doi-asserted-by":"crossref","unstructured":"Xu, X.: Visually informed binaural audio generation without binaural audios. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.01523"},{"key":"6_CR35","doi-asserted-by":"crossref","unstructured":"Yeh, H.: Wave-ray coupling for interactive sound propagation in large complex scenes. ACM Trans. Graph. TOG (6) (2013)","DOI":"10.1145\/2508363.2508420"},{"key":"6_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1007\/978-3-030-58610-2_4","volume-title":"Computer Vision \u2013 ECCV 2020","author":"H Zhou","year":"2020","unstructured":"Zhou, H., Xu, X., Lin, D., Wang, X., Liu, Z.: Sep-Stereo: Visually Guided Stereophonic Audio Generation by Associating Source Separation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12357, pp. 52\u201369. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58610-2_4"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-31663-9_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T05:48:30Z","timestamp":1785649710000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-31663-9_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,3]]},"ISBN":["9783032316622","9783032316639"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-31663-9_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,3]]},"assertion":[{"value":"3 August 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lyon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 August 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 August 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2026.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}