{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T19:07:30Z","timestamp":1782932850962,"version":"3.54.5"},"publisher-location":"Cham","reference-count":62,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726262","type":"print"},{"value":"9783031726279","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T00:00:00Z","timestamp":1729382400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T00:00:00Z","timestamp":1729382400000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-72627-9_26","type":"book-chapter","created":{"date-parts":[[2024,10,19]],"date-time":"2024-10-19T21:02:10Z","timestamp":1729371730000},"page":"459-476","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":50,"title":["HeadGaS: Real-Time Animatable Head Avatars via\u00a03D Gaussian Splatting"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1163-7448","authenticated-orcid":false,"given":"Helisa","family":"Dhamo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7023-6797","authenticated-orcid":false,"given":"Yinyu","family":"Nie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2925-3316","authenticated-orcid":false,"given":"Arthur","family":"Moreau","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3381-6685","authenticated-orcid":false,"given":"Jifei","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3141-5562","authenticated-orcid":false,"given":"Richard","family":"Shaw","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9021-5042","authenticated-orcid":false,"given":"Yiren","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9096-4740","authenticated-orcid":false,"given":"Eduardo","family":"P\u00e9rez-Pellitero","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,20]]},"reference":[{"key":"26_CR1","doi-asserted-by":"crossref","unstructured":"Barron, J.T., et al.: Mip-NeRF: a multiscale representation for anti-aliasing neural radiance fields. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00580"},{"key":"26_CR2","doi-asserted-by":"crossref","unstructured":"Barron, J.T., Mildenhall, B., Verbin, D., Srinivasan, P.P., Hedman, P.: Mip-NeRF 360: unbounded anti-aliased neural radiance fields. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00539"},{"key":"26_CR3","doi-asserted-by":"crossref","unstructured":"Barron, J.T., Mildenhall, B., Verbin, D., Srinivasan, P.P., Hedman, P.: Zip-NeRF: anti-aliased grid-based neural radiance fields. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01804"},{"key":"26_CR4","doi-asserted-by":"crossref","unstructured":"Bharadwaj, S., Zheng, Y., Hilliges, O., Black, M.J., Abrevaya, V.F.: FLARE: fast learning of animatable and relightable mesh avatars. ACM TOG (2023)","DOI":"10.1145\/3618401"},{"key":"26_CR5","doi-asserted-by":"crossref","unstructured":"Blanz, V., Vetter, T.: A morphable model for the synthesis of 3D faces. In: Conference on Computer Graphics and Interactive Techniques, SIGGRAPH (1999)","DOI":"10.1145\/311535.311556"},{"key":"26_CR6","unstructured":"Cao, C., Weng, Y., Zhou, S., Tong, Y., Zhou, K.: FaceWarehouse: a 3D facial expression database for visual computing. IEEE Trans. Vis. Comput. Graph. (2014)"},{"key":"26_CR7","doi-asserted-by":"crossref","unstructured":"Catley-Chandar, S., Shaw, R., Slabaugh, G., P\u00e9rez-Pellitero, E.: RoGUENeRF: a robust geometry-consistent universal enhancer for NeRF. In: ECCV (2024)","DOI":"10.1007\/978-3-031-73254-6_4"},{"key":"26_CR8","doi-asserted-by":"crossref","unstructured":"Chen, A., Xu, Z., Geiger, A., Yu, J., Su, H.: TensoRF: tensorial radiance fields. In: ECCV (2022)","DOI":"10.1007\/978-3-031-19824-3_20"},{"key":"26_CR9","unstructured":"Chen, J., et al.: Animatable neural radiance fields from monocular rgb videos. ArXiv abs\/2106.13629 (2021)"},{"key":"26_CR10","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: MonoGaussianAvatar: monocular gaussian point-based head avatar. In: ACM SIGGRAPH Conference Proceedings (2024)","DOI":"10.1145\/3641519.3657499"},{"key":"26_CR11","doi-asserted-by":"crossref","unstructured":"Deng, K., Liu, A., Zhu, J.Y., Ramanan, D.: Depth-supervised NeRF: fewer views and faster training for free. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01254"},{"key":"26_CR12","doi-asserted-by":"crossref","unstructured":"Du, Y., Zhang, Y., Yu, H.X., Tenenbaum, J.B., Wu, J.: Neural radiance flow for 4D view synthesis and video processing. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01406"},{"key":"26_CR13","doi-asserted-by":"crossref","unstructured":"Gafni, G., Thies, J., Zollh\u00f6fer, M., Nie\u00dfner, M.: Dynamic neural radiance fields for monocular 4D facial avatar reconstruction. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00854"},{"key":"26_CR14","doi-asserted-by":"crossref","unstructured":"Gao, X., Zhong, C., Xiang, J., Hong, Y., Guo, Y., Zhang, J.: Reconstructing personalized semantic facial nerf models from monocular video. In: ACM TOG (Proceedings of SIGGRAPH Asia) (2022)","DOI":"10.1145\/3550454.3555501"},{"key":"26_CR15","doi-asserted-by":"crossref","unstructured":"Garrido, P., Valgaerts, L., Rehmsen, O., Thorm\u00e4hlen, T., P\u00e9rez, P., Theobalt, C.: Automatic face reenactment. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.537"},{"key":"26_CR16","doi-asserted-by":"crossref","unstructured":"Grassal, P.W., Prinzler, M., Leistner, T., Rother, C., Nie\u00dfner, M., Thies, J.: Neural head avatars from monocular RGB videos. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01810"},{"key":"26_CR17","doi-asserted-by":"crossref","unstructured":"Hong, Y., Peng, B., Xiao, H., Liu, L., Zhang, J.: HeadNeRF: a real-time nerf-based parametric head model. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01973"},{"key":"26_CR18","doi-asserted-by":"crossref","unstructured":"Jang, Y., et al.: VSCHH 2023: a benchmark for the view synthesis challenge of human heads. In: Proceedings of the IEEE\/CVF ICCV Workshops (2023)","DOI":"10.1109\/ICCVW60793.2023.00120"},{"key":"26_CR19","doi-asserted-by":"crossref","unstructured":"Johnson, J., Alahi, A., Fei-Fei, L.: Perceptual losses for real-time style transfer and super-resolution. In: ECCV (2016)","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"26_CR20","doi-asserted-by":"crossref","unstructured":"Kerbl, B., Kopanas, G., Leimk\u00fchler, T., Drettakis, G.: 3D gaussian splatting for real-time radiance field rendering. ACM TOG 42(4), 139\u20131 (2023)","DOI":"10.1145\/3592433"},{"key":"26_CR21","doi-asserted-by":"crossref","unstructured":"Kim, H., et al.: Deep video portraits. ACM TOG (2018)","DOI":"10.1145\/3197517.3201283"},{"key":"26_CR22","doi-asserted-by":"crossref","unstructured":"Kirschstein, T., Qian, S., Giebenhain, S., Walter, T., Nie\u00dfner, M.: NeRSemble: multi-view radiance field reconstruction of human heads. ACM TOG 42(4), 1\u201314 (2023)","DOI":"10.1145\/3592455"},{"key":"26_CR23","doi-asserted-by":"crossref","unstructured":"Kocabas, M., Chang, R., Gabriel, J., Tuzel, O., Ranjan, A.: Hugs: human gaussian splats. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00055"},{"key":"26_CR24","doi-asserted-by":"crossref","unstructured":"Li, T., Bolkart, T., Black, M.J., Li, H., Romero, J.: Learning a model of facial shape and expression from 4D scans. ACM TOG, (Proc. SIGGRAPH Asia) (2017)","DOI":"10.1145\/3130800.3130813"},{"key":"26_CR25","doi-asserted-by":"crossref","unstructured":"Li, Z., Niklaus, S., Snavely, N., Wang, O.: Neural scene flow fields for space-time view synthesis of dynamic scenes. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00643"},{"key":"26_CR26","doi-asserted-by":"crossref","unstructured":"Lin, S., Yang, L., Saleemi, I., Sengupta, S.: Robust high-resolution video matting with temporal guidance. In: WACV (2022)","DOI":"10.1109\/WACV51458.2022.00319"},{"key":"26_CR27","doi-asserted-by":"crossref","unstructured":"Lombardi, S., Saragih, J., Simon, T., Sheikh, Y.: Deep appearance models for face rendering. ACM TOG 37(4), 1\u201313 (2018)","DOI":"10.1145\/3197517.3201401"},{"key":"26_CR28","doi-asserted-by":"crossref","unstructured":"Lombardi, S., Simon, T., Schwartz, G., Zollhoefer, M., Sheikh, Y., Saragih, J.: Mixture of volumetric primitives for efficient neural rendering. ACM TOG 40(4), 1\u201313 (2021)","DOI":"10.1145\/3476576.3476608"},{"key":"26_CR29","doi-asserted-by":"crossref","unstructured":"Luiten, J., Kopanas, G., Leibe, B., Ramanan, D.: Dynamic 3D gaussians: tracking by persistent dynamic view synthesis. In: 3DV (2024)","DOI":"10.1109\/3DV62453.2024.00044"},{"key":"26_CR30","doi-asserted-by":"crossref","unstructured":"Mihajlovic, M., Bansal, A., Zollhoefer, M., Tang, S., Saito, S.: KeypointNeRF: Generalizing image-based volumetric avatars using relative spatial encoding of keypoints. In: ECCV (2022)","DOI":"10.1007\/978-3-031-19784-0_11"},{"key":"26_CR31","doi-asserted-by":"crossref","unstructured":"Mildenhall, B., Srinivasan, P.P., Tancik, M., Barron, J.T., Ramamoorthi, R., Ng, R.: NeRF: representing scenes as neural radiance fields for view synthesis. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"26_CR32","doi-asserted-by":"crossref","unstructured":"Moreau, A., Song, J., Dhamo, H., Shaw, R., Zhou, Y., P\u00e9rez-Pellitero, E.: Human gaussian splatting: real-time rendering of animatable avatars. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00081"},{"key":"26_CR33","doi-asserted-by":"crossref","unstructured":"M\u00fcller, T., Evans, A., Schied, C., Keller, A.: Instant neural graphics primitives with a multiresolution hash encoding. ACM Trans, Graph 41(4), 1\u201315 (2022)","DOI":"10.1145\/3528223.3530127"},{"key":"26_CR34","doi-asserted-by":"crossref","unstructured":"Niemeyer, M., Barron, J.T., Mildenhall, B., Sajjadi, M.S.M., Geiger, A., Radwan, N.: RegNeRF: regularizing neural radiance fields for view synthesis from sparse inputs. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00540"},{"key":"26_CR35","doi-asserted-by":"crossref","unstructured":"Park, J.J., Florence, P., Straub, J., Newcombe, R., Lovegrove, S.: DeepSDF: learning continuous signed distance functions for shape representation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00025"},{"key":"26_CR36","doi-asserted-by":"crossref","unstructured":"Park, K., et al.: Nerfies: deformable neural radiance fields. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00581"},{"key":"26_CR37","doi-asserted-by":"crossref","unstructured":"Park, K., et al.: HyperNeRF: a higher-dimensional representation for topologically varying neural radiance fields. ACM TOG (2021)","DOI":"10.1145\/3478513.3480487"},{"key":"26_CR38","doi-asserted-by":"crossref","unstructured":"Peng, S., et al.: Animatable neural radiance fields for modeling dynamic human bodies. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01405"},{"key":"26_CR39","doi-asserted-by":"crossref","unstructured":"Pumarola, A., Corona, E., Pons-Moll, G., Moreno-Noguer, F.: D-NeRF: neural radiance fields for dynamic scenes. In: CVPR (2020)","DOI":"10.1109\/CVPR46437.2021.01018"},{"key":"26_CR40","doi-asserted-by":"crossref","unstructured":"Qian, S., Kirschstein, T., Schoneveld, L., Davoli, D., Giebenhain, S., Nie\u00dfner, M.: GaussianAvatars: photorealistic head avatars with rigged 3d gaussians. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01919"},{"key":"26_CR41","unstructured":"Ruder, S.: An overview of gradient descent optimization algorithms. arXiv preprint arXiv:1609.04747 (2016)"},{"key":"26_CR42","doi-asserted-by":"crossref","unstructured":"Sch\u00f6nberger, J.L., Frahm, J.M.: Structure-from-motion revisited. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.445"},{"key":"26_CR43","doi-asserted-by":"crossref","unstructured":"Shaw, R., et al.: Swings: sliding windows for dynamic 3D gaussian splatting. In: ECCV (2024)","DOI":"10.1007\/978-3-031-73001-6_3"},{"key":"26_CR44","doi-asserted-by":"crossref","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2015)","DOI":"10.1109\/ICCV.2015.314"},{"key":"26_CR45","doi-asserted-by":"crossref","unstructured":"Sun, C., Sun, M., Chen, H.: Direct voxel grid optimization: super-fast convergence for radiance fields reconstruction. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00538"},{"key":"26_CR46","doi-asserted-by":"crossref","unstructured":"Tretschk, E., Tewari, A., Golyanik, V., Zollh\u00f6fer, M., Lassner, C., Theobalt, C.: Non-rigid neural radiance fields: reconstruction and novel view synthesis of a dynamic scene from monocular video. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01272"},{"key":"26_CR47","doi-asserted-by":"crossref","unstructured":"Truong, P., Rakotosaona, M.J., Manhardt, F., Tombari, F.: SPARF: neural radiance fields from sparse and noisy poses. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00408"},{"key":"26_CR48","doi-asserted-by":"crossref","unstructured":"Wang, D., Chandran, P., Zoss, G., Bradley, D., Gotardo, P.F.U.: MoRF: morphable radiance fields for multiview neural head modeling. In: ACM SIGGRAPH 2022 Conference Proceedings (2022)","DOI":"10.1145\/3528233.3530753"},{"key":"26_CR49","unstructured":"Wang, J., Xie, J.C., Li, X., Xu, F., Pun, C.M., Gao, H.: Gaussianhead: high-fidelity head avatars with learnable gaussian derivation. ArXiv:2312.01632 (2024)"},{"key":"26_CR50","doi-asserted-by":"crossref","unstructured":"Weng, C.Y., Curless, B., Srinivasan, P.P., Barron, J.T., Kemelmacher-Shlizerman, I.: HumanNeRF: free-viewpoint rendering of moving people from monocular video. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01573"},{"key":"26_CR51","doi-asserted-by":"crossref","unstructured":"Wu, G., et al.: 4D gaussian splatting for real-time dynamic scene rendering. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01920"},{"key":"26_CR52","doi-asserted-by":"crossref","unstructured":"Xiang, J., Gao, X., Guo, Y., Zhang, J.: FlashAvatar: high-fidelity head avatar with efficient gaussian embedding. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00177"},{"key":"26_CR53","unstructured":"Xu, B., Wang, N., Chen, T., Li, M.: Empirical evaluation of rectified activations in convolutional network (2015)"},{"key":"26_CR54","doi-asserted-by":"crossref","unstructured":"Xu, Y., et al.: Gaussian head avatar: ultra high-fidelity head avatar via dynamic gaussians. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00189"},{"key":"26_CR55","doi-asserted-by":"crossref","unstructured":"Xu, Y., Wang, L., Zhao, X., Zhang, H., Liu, Y.: AvatarMAV: fast 3D head avatar reconstruction using motion-aware neural voxels. In: ACM SIGGRAPH (2023)","DOI":"10.1145\/3588432.3591567"},{"key":"26_CR56","doi-asserted-by":"crossref","unstructured":"Yang, Z., Gao, X., Zhou, W., Jiao, S., Zhang, Y., Jin, X.: Deformable 3D gaussians for high-fidelity monocular dynamic scene reconstruction. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01922"},{"key":"26_CR57","doi-asserted-by":"crossref","unstructured":"Yifan, W., Serena, F., Wu, S., \u00d6ztireli, C., Sorkine-Hornung, O.: Differentiable surface splatting for point-based geometry processing. ACM TOG (Proceedings of ACM SIGGRAPH ASIA) (2019)","DOI":"10.1145\/3355089.3356513"},{"key":"26_CR58","doi-asserted-by":"crossref","unstructured":"Yu, C., Gao, C., Wang, J., Yu, G., Shen, C., Sang, N.: BiseNet V2: bilateral network with guided aggregation for real-time semantic segmentation. In: IJCV (2021)","DOI":"10.1007\/s11263-021-01515-2"},{"key":"26_CR59","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"26_CR60","doi-asserted-by":"crossref","unstructured":"Zheng, Y., Abrevaya, V.F., B\u00fchler, M.C., Chen, X., Black, M.J., Hilliges, O.: I M Avatar: implicit morphable head avatars from videos. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01318"},{"key":"26_CR61","doi-asserted-by":"crossref","unstructured":"Zheng, Y., Yifan, W., Wetzstein, G., Black, M.J., Hilliges, O.: PointAvatar: deformable point-based head avatars from videos. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02017"},{"key":"26_CR62","doi-asserted-by":"crossref","unstructured":"Zielonka, W., Bolkart, T., Thies, J.: Instant volumetric head avatars. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00444"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72627-9_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,29]],"date-time":"2024-11-29T22:45:15Z","timestamp":1732920315000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72627-9_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,20]]},"ISBN":["9783031726262","9783031726279"],"references-count":62,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72627-9_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,20]]},"assertion":[{"value":"20 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}