{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T15:57:55Z","timestamp":1774022275872,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":67,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,10]]},"DOI":"10.1145\/3721238.3730737","type":"proceedings-article","created":{"date-parts":[[2025,7,23]],"date-time":"2025-07-23T08:42:43Z","timestamp":1753260163000},"page":"1-10","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["GAIA: Generative Animatable Interactive Avatars with Expression-conditioned Gaussians"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-0553-8125","authenticated-orcid":false,"given":"Zhengming","family":"Yu","sequence":"first","affiliation":[{"name":"NVIDIA, Santa Clara, USA and Texas A&M University, College Station, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9422-5782","authenticated-orcid":false,"given":"Tianye","family":"Li","sequence":"additional","affiliation":[{"name":"NVIDIA, Santa Clara, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2966-9501","authenticated-orcid":false,"given":"Jingxiang","family":"Sun","sequence":"additional","affiliation":[{"name":"NVIDIA, Beijing, China and Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8850-9259","authenticated-orcid":false,"given":"Omer","family":"Shapira","sequence":"additional","affiliation":[{"name":"NVIDIA, New York, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7992-3876","authenticated-orcid":false,"given":"Seonwook","family":"Park","sequence":"additional","affiliation":[{"name":"NVIDIA, Santa Clara, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6234-936X","authenticated-orcid":false,"given":"Michael","family":"Stengel","sequence":"additional","affiliation":[{"name":"NVIDIA, Santa Clara, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1704-1013","authenticated-orcid":false,"given":"Matthew","family":"Chan","sequence":"additional","affiliation":[{"name":"NVIDIA, Santa Clara, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0144-9489","authenticated-orcid":false,"given":"Xin","family":"Li","sequence":"additional","affiliation":[{"name":"Texas A&M University, College Station, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2284-3952","authenticated-orcid":false,"given":"Wenping","family":"Wang","sequence":"additional","affiliation":[{"name":"Texas A&M University, College Station, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6815-4864","authenticated-orcid":false,"given":"Koki","family":"Nagano","sequence":"additional","affiliation":[{"name":"NVIDIA, Los Angeles, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0213-2860","authenticated-orcid":false,"given":"Shalini","family":"De Mello","sequence":"additional","affiliation":[{"name":"NVIDIA, Santa Clara, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,7,27]]},"reference":[{"key":"e_1_3_3_3_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00902"},{"key":"e_1_3_3_3_3_1","doi-asserted-by":"crossref","unstructured":"O Alexander M Rogers W Lambeth J Chiang W Ma C Wang and P Debevec. 2009. The digital emily project: Achieving a photoreal digital actor. IEEE Computer Graphics and Applications 30 (2009).","DOI":"10.1145\/1667239.1667251"},{"key":"e_1_3_3_3_4_1","doi-asserted-by":"crossref","unstructured":"Alexander Bergman Petr Kellnhofer Wang Yifan Eric Chan David Lindell and Gordon Wetzstein. 2022. Generative neural articulated radiance fields. Advances in Neural Information Processing Systems 35 (2022) 19900\u201319916.","DOI":"10.52202\/068431-1447"},{"key":"e_1_3_3_3_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/311535.311556"},{"key":"e_1_3_3_3_6_1","doi-asserted-by":"crossref","unstructured":"Robert\u00a0C Bolles H\u00a0Harlyn Baker and David\u00a0H Marimont. 1987. Epipolar-plane image analysis: An approach to determining structure from motion. International journal of computer vision 1 1 (1987) 7\u201355.","DOI":"10.1007\/BF00128525"},{"key":"e_1_3_3_3_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00395"},{"key":"e_1_3_3_3_8_1","doi-asserted-by":"crossref","unstructured":"Chen Cao Derek Bradley Kun Zhou and Thabo Beeler. 2015. Real-time high-fidelity facial performance capture. ACM Transactions on Graphics (ToG) 34 4 (2015) 1\u20139.","DOI":"10.1145\/2766943"},{"key":"e_1_3_3_3_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01565"},{"key":"e_1_3_3_3_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00574"},{"key":"e_1_3_3_3_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00222"},{"key":"e_1_3_3_3_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657499"},{"key":"e_1_3_3_3_13_1","unstructured":"Xuangeng Chu and Tatsuya Harada. 2024. Generalizable and Animatable Gaussian Head Avatar. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.07971 (2024)."},{"key":"e_1_3_3_3_14_1","doi-asserted-by":"crossref","unstructured":"Hang Dai Nick Pears William Smith and Christian Duncan. 2020. Statistical modeling of craniofacial shape and texture. International Journal of Computer Vision 128 2 (2020) 547\u2013571.","DOI":"10.1007\/s11263-019-01260-7"},{"key":"e_1_3_3_3_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00680"},{"key":"e_1_3_3_3_16_1","doi-asserted-by":"crossref","unstructured":"Yu Deng Duomin Wang and Baoyuan Wang. 2024a. Portrait4D-v2: Pseudo Multi-View Data Creates Better 4D Head Synthesizer. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.13570 (2024).","DOI":"10.1007\/978-3-031-72643-9_19"},{"key":"e_1_3_3_3_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01041"},{"key":"e_1_3_3_3_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00038"},{"key":"e_1_3_3_3_19_1","first-page":"1","volume-title":"Data-driven 3D facial animation","author":"Deng Zhigang","year":"2008","unstructured":"Zhigang Deng and Junyong Noh. 2008. Computer facial animation: A survey. In Data-driven 3D facial animation. Springer, 1\u201328."},{"key":"e_1_3_3_3_20_1","doi-asserted-by":"crossref","unstructured":"Ian Goodfellow Jean Pouget-Abadie Mehdi Mirza Bing Xu David Warde-Farley Sherjil Ozair Aaron Courville and Yoshua Bengio. 2020. Generative adversarial networks. Commun. ACM 63 11 (2020) 139\u2013144.","DOI":"10.1145\/3422622"},{"key":"e_1_3_3_3_21_1","doi-asserted-by":"crossref","unstructured":"Paulo Gotardo J\u00e9r\u00e9my Riviere Derek Bradley Abhijeet Ghosh and Thabo Beeler. 2018. Practical dynamic facial appearance modeling and acquisition. ACM Transactions on Graphics (ToG) 37 6 (2018) 1\u201313.","DOI":"10.1145\/3272127.3275073"},{"key":"e_1_3_3_3_22_1","volume-title":"International Conference on Learning Representations","author":"Gu Jiatao","year":"2022","unstructured":"Jiatao Gu, Lingjie Liu, Peng Wang, and Christian Theobalt. 2022. StyleNeRF: A Style-based 3D Aware Generator for High-resolution Image Synthesis. In International Conference on Learning Representations."},{"key":"e_1_3_3_3_23_1","first-page":"9984","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Henzler Philipp","year":"2019","unstructured":"Philipp Henzler, Niloy\u00a0J Mitra, and Tobias Ritschel. 2019. Escaping plato\u2019s cave: 3d shape from adversarial rendering. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 9984\u20139993."},{"key":"e_1_3_3_3_24_1","unstructured":"Martin Heusel Hubert Ramsauer Thomas Unterthiner Bernhard Nessler and Sepp Hochreiter. 2017. Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_3_3_25_1","volume-title":"International Conference on Learning Representations","author":"Hong Fangzhou","year":"2023","unstructured":"Fangzhou Hong, Zhaoxi Chen, LAN Yushi, Liang Pan, and Ziwei Liu. 2023. EVA3D: Compositional 3D Human Generation from 2D Image Collections. In International Conference on Learning Representations."},{"key":"e_1_3_3_3_26_1","first-page":"20374","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Hong Yang","year":"2022","unstructured":"Yang Hong, Bo Peng, Haiyao Xiao, Ligang Liu, and Juyong Zhang. 2022. Headnerf: A real-time nerf-based parametric head model. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 20374\u201320384."},{"key":"e_1_3_3_3_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"e_1_3_3_3_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"e_1_3_3_3_29_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19999"},{"key":"e_1_3_3_3_30_1","doi-asserted-by":"crossref","unstructured":"Bernhard Kerbl Georgios Kopanas Thomas Leimk\u00fchler and George Drettakis. 2023. 3D Gaussian Splatting for Real-Time Radiance Field Rendering. ACM Trans. Graph. 42 4 (2023) 139\u20131.","DOI":"10.1145\/3592433"},{"key":"e_1_3_3_3_31_1","doi-asserted-by":"crossref","unstructured":"Tobias Kirschstein Simon Giebenhain Jiapeng Tang Markos Georgopoulos and Matthias Nie\u00dfner. 2024. GGHead: Fast and Generalizable 3D Gaussian Heads. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.09377 (2024).","DOI":"10.1145\/3680528.3687686"},{"key":"e_1_3_3_3_32_1","doi-asserted-by":"crossref","unstructured":"Tobias Kirschstein Shenhan Qian Simon Giebenhain Tim Walter and Matthias Nie\u00dfner. 2023. Nersemble: Multi-view radiance field reconstruction of human heads. ACM Transactions on Graphics (TOG) 42 4 (2023) 1\u201314.","DOI":"10.1145\/3592455"},{"key":"e_1_3_3_3_33_1","doi-asserted-by":"crossref","unstructured":"Tianye Li Timo Bolkart Michael\u00a0J Black Hao Li and Javier Romero. 2017. Learning a model of facial shape and expression from 4D scans. ACM Trans. Graph. 36 6 (2017) 194\u20131.","DOI":"10.1145\/3130800.3130813"},{"key":"e_1_3_3_3_34_1","unstructured":"Xueting Li Shalini De\u00a0Mello Sifei Liu Koki Nagano Umar Iqbal and Jan Kautz. 2024. Generalizable one-shot 3D neural head avatar. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_3_3_35_1","unstructured":"Stephen Lombardi Tomas Simon Jason Saragih Gabriel Schwartz Andreas Lehrmann and Yaser Sheikh. 2019. Neural volumes: Learning dynamic renderable volumes from images. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1906.07751 (2019)."},{"key":"e_1_3_3_3_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3596711.3596800"},{"key":"e_1_3_3_3_37_1","first-page":"3481","volume-title":"International conference on machine learning","author":"Mescheder Lars","year":"2018","unstructured":"Lars Mescheder, Andreas Geiger, and Sebastian Nowozin. 2018. Which training methods for GANs do actually converge?. In International conference on machine learning. PMLR, 3481\u20133490."},{"key":"e_1_3_3_3_38_1","doi-asserted-by":"crossref","unstructured":"Ben Mildenhall Pratul\u00a0P Srinivasan Matthew Tancik Jonathan\u00a0T Barron Ravi Ramamoorthi and Ren Ng. 2021. Nerf: Representing scenes as neural radiance fields for view synthesis. Commun. ACM 65 1 (2021) 99\u2013106.","DOI":"10.1145\/3503250"},{"key":"e_1_3_3_3_39_1","doi-asserted-by":"crossref","unstructured":"Koki Nagano Graham Fyffe Oleg Alexander Jernej Barbic Hao Li Abhijeet Ghosh and Paul\u00a0E Debevec. 2015. Skin microstructure deformation with displacement map convolution. ACM Trans. Graph. 34 4 (2015) 109\u20131.","DOI":"10.1145\/2766894"},{"key":"e_1_3_3_3_40_1","first-page":"7588","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Nguyen-Phuoc Thu","year":"2019","unstructured":"Thu Nguyen-Phuoc, Chuan Li, Lucas Theis, Christian Richardt, and Yong-Liang Yang. 2019. Hologan: Unsupervised learning of 3d representations from natural images. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 7588\u20137597."},{"key":"e_1_3_3_3_41_1","unstructured":"Thu\u00a0H Nguyen-Phuoc Christian Richardt Long Mai Yongliang Yang and Niloy Mitra. 2020. Blockgan: Learning 3d object-aware scene representations from unlabelled images. Advances in neural information processing systems 33 (2020) 6767\u20136778."},{"key":"e_1_3_3_3_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01129"},{"key":"e_1_3_3_3_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_36"},{"key":"e_1_3_3_3_44_1","unstructured":"Adam Paszke Sam Gross Francisco Massa Adam Lerer James Bradbury Gregory Chanan Trevor Killeen Zeming Lin Natalia Gimelshein Luca Antiga et\u00a0al. 2019. Pytorch: An imperative style high-performance deep learning library. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_3_3_45_1","doi-asserted-by":"crossref","unstructured":"Stylianos Ploumpis Evangelos Ververas Eimear O\u2019Sullivan Stylianos Moschoglou Haoyang Wang Nick Pears William\u00a0AP Smith Baris Gecer and Stefanos Zafeiriou. 2020. Towards a complete 3D morphable model of the human head. IEEE transactions on pattern analysis and machine intelligence 43 11 (2020) 4142\u20134160.","DOI":"10.1109\/TPAMI.2020.2991150"},{"key":"e_1_3_3_3_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01919"},{"key":"e_1_3_3_3_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00241"},{"key":"e_1_3_3_3_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00021"},{"key":"e_1_3_3_3_49_1","unstructured":"Katja Schwarz Yiyi Liao Michael Niemeyer and Andreas Geiger. 2020. Graf: Generative radiance fields for 3d-aware image synthesis. Advances in Neural Information Processing Systems 33 (2020) 20154\u201320166."},{"key":"e_1_3_3_3_50_1","doi-asserted-by":"crossref","unstructured":"Ivan Skorokhodov Sergey Tulyakov Yiqun Wang and Peter Wonka. 2022. Epigraf: Rethinking training of 3d gans. Advances in Neural Information Processing Systems 35 (2022) 24487\u201324501.","DOI":"10.52202\/068431-1778"},{"key":"e_1_3_3_3_51_1","doi-asserted-by":"crossref","unstructured":"Jingxiang Sun Xuan Wang Yichun Shi Lizhen Wang Jue Wang and Yebin Liu. 2022. Ide-3d: Interactive disentangled editing for high-resolution 3d-aware portrait synthesis. ACM Transactions on Graphics (ToG) 41 6 (2022) 1\u201310.","DOI":"10.1145\/3550454.3555506"},{"key":"e_1_3_3_3_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02011"},{"key":"e_1_3_3_3_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/2929464.2929475"},{"key":"e_1_3_3_3_54_1","doi-asserted-by":"crossref","unstructured":"Phong Tran Egor Zakharov Long-Nhat Ho Adilbek Karmanov Ariana Bermudez\u00a0Venegas McLean Goldwhite Aviral Agarwal Liwen Hu Anh Tran and Hao Li. 2024. VOODOO XP: Expressive One-Shot Head Reenactment for VR Telepresence. ACM Trans. Graph. 43 6 Article 253 (Nov. 2024) 26\u00a0pages. https:\/\/doi.org\/10.1145\/3687974","DOI":"10.1145\/3687974"},{"key":"e_1_3_3_3_55_1","doi-asserted-by":"crossref","unstructured":"Alex Trevithick Matthew Chan Michael Stengel Eric Chan Chao Liu Zhiding Yu Sameh Khamis Manmohan Chandraker Ravi Ramamoorthi and Koki Nagano. 2023. Real-Time Radiance Fields for Single-Image Portrait View Synthesis. ACM Trans. Graph. 42 4 Article 135 (July 2023) 15\u00a0pages. https:\/\/doi.org\/10.1145\/3592460","DOI":"10.1145\/3592460"},{"key":"e_1_3_3_3_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02148"},{"key":"e_1_3_3_3_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00991"},{"key":"e_1_3_3_3_58_1","doi-asserted-by":"crossref","unstructured":"Yue Wu Yu Deng Jiaolong Yang Fangyun Wei Qifeng Chen and Xin Tong. 2022. Anifacegan: Animatable 3d-aware face image generation for video avatars. Advances in Neural Information Processing Systems 35 (2022) 36188\u201336201.","DOI":"10.52202\/068431-2622"},{"key":"e_1_3_3_3_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00177"},{"key":"e_1_3_3_3_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00209"},{"key":"e_1_3_3_3_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00189"},{"key":"e_1_3_3_3_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01789"},{"key":"e_1_3_3_3_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00955"},{"key":"e_1_3_3_3_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_3_3_65_1","doi-asserted-by":"crossref","unstructured":"Xiaochen Zhao Lizhen Wang Jingxiang Sun Hongwen Zhang Jinli Suo and Yebin Liu. 2023. Havatar: High-fidelity head avatar via facial model conditioned neural radiance field. ACM Transactions on Graphics 43 1 (2023) 1\u201316.","DOI":"10.1145\/3626316"},{"key":"e_1_3_3_3_66_1","first-page":"13545","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Zheng Yufeng","year":"2022","unstructured":"Yufeng Zheng, Victoria\u00a0Fern\u00e1ndez Abrevaya, Marcel\u00a0C B\u00fchler, Xu Chen, Michael\u00a0J Black, and Otmar Hilliges. 2022. Im avatar: Implicit morphable head avatars from videos. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 13545\u201313555."},{"key":"e_1_3_3_3_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02017"},{"key":"e_1_3_3_3_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00444"}],"event":{"name":"SIGGRAPH Conference Papers '25: Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","location":"Vancouver BC Canada","acronym":"SIGGRAPH Conference Papers '25","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3721238.3730737","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T14:59:08Z","timestamp":1774018748000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3721238.3730737"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,27]]},"references-count":67,"alternative-id":["10.1145\/3721238.3730737","10.1145\/3721238"],"URL":"https:\/\/doi.org\/10.1145\/3721238.3730737","relation":{},"subject":[],"published":{"date-parts":[[2025,7,27]]},"assertion":[{"value":"2025-07-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}