{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T16:25:23Z","timestamp":1782318323190,"version":"3.54.5"},"reference-count":74,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2024,2,16]],"date-time":"2024-02-16T00:00:00Z","timestamp":1708041600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,2,16]],"date-time":"2024-02-16T00:00:00Z","timestamp":1708041600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"NTU NAP, MOE AcRF Tier 1","award":["2021-T1-001-088"],"award-info":[{"award-number":["2021-T1-001-088"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1007\/s11263-024-02007-9","type":"journal-article","created":{"date-parts":[[2024,2,16]],"date-time":"2024-02-16T16:02:41Z","timestamp":1708099361000},"page":"2713-2728","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["ReliTalk: Relightable Talking Portrait Generation from a Single Video"],"prefix":"10.1007","volume":"132","author":[{"given":"Haonan","family":"Qiu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaoxi","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuming","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hang","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangyu","family":"Fan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wayne","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4220-5958","authenticated-orcid":false,"given":"Ziwei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,2,16]]},"reference":[{"key":"2007_CR1","unstructured":"Amodei, D., Ananthanarayanan, S., Anubhai, R., Bai, J., Battenberg, E., Case, C., Casper, J., Catanzaro, B., Cheng, Q., & Chen, G., et\u00a0al. (2016). Deep speech 2: End-to-end speech recognition in english and mandarin. In International conference on machine learning, pp. 173\u2013182."},{"issue":"8","key":"2007_CR2","doi-asserted-by":"publisher","first-page":"1670","DOI":"10.1109\/TPAMI.2014.2377712","volume":"37","author":"JT Barron","year":"2014","unstructured":"Barron, J. T., & Malik, J. (2014). Shape, illumination, and reflectance from shading. IEEE Transactions on Pattern Analysis and Machine Intelligence, 37(8), 1670\u20131687.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2007_CR3","doi-asserted-by":"crossref","unstructured":"Barron, J. T., Mildenhall, B., Tancik, M., Hedman, P., Martin-Brualla, R., & Srinivasan, P. P. (2021a). Mip-NeRF: A multiscale representation for anti-aliasing neural radiance fields. arXiv:2103.13415 [cs].","DOI":"10.1109\/ICCV48922.2021.00580"},{"key":"2007_CR4","doi-asserted-by":"crossref","unstructured":"Barron, J. T., Mildenhall, B., Verbin, D., Srinivasan, P. P., & Hedman, P. (2021b). Mip-NeRF 360: Unbounded anti-aliased neural radiance fields. arXiv:2111.12077 [cs].","DOI":"10.1109\/CVPR52688.2022.00539"},{"issue":"2","key":"2007_CR5","doi-asserted-by":"publisher","first-page":"218","DOI":"10.1109\/TPAMI.2003.1177153","volume":"25","author":"R Basri","year":"2003","unstructured":"Basri, R., & Jacobs, D. W. (2003). Lambertian reflectance and linear subspaces. IEEE Transactions on Pattern Analysis and Machine Intelligence, 25(2), 218\u2013233.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2007_CR6","doi-asserted-by":"crossref","unstructured":"Blanz, V., & Vetter, T. (1999). A morphable model for the synthesis of 3d faces. In Proceedings of the 26th annual conference on Computer graphics and interactive techniques, pp. 187\u2013194.","DOI":"10.1145\/311535.311556"},{"key":"2007_CR7","doi-asserted-by":"crossref","unstructured":"Blinn, J. F. (1977). Models of light reflection for computer synthesized pictures. In Proceedings of the 4th annual conference on computer graphics and interactive techniques, pp. 192\u2013198.","DOI":"10.1145\/563858.563893"},{"key":"2007_CR8","doi-asserted-by":"crossref","unstructured":"Caselles, P., Ramon, E., Garcia, J., Giro-i Nieto, X., Moreno-Noguer, F., & Triginer, G. (2023). Sira: Relightable avatars from a single image. In Proceedings of the IEEE\/CVF winter conference on applications of computer vision, pp. 775\u2013784.","DOI":"10.1109\/WACV56688.2023.00084"},{"key":"2007_CR9","doi-asserted-by":"crossref","unstructured":"Chan, E.R., Monteiro, M., Kellnhofer, P., Wu, J., & Wetzstein, G. (2021). pi-gan: Periodic implicit generative adversarial networks for 3d-aware image synthesis. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 5799\u20135809.","DOI":"10.1109\/CVPR46437.2021.00574"},{"key":"2007_CR10","doi-asserted-by":"crossref","unstructured":"Chan, E. R., Lin, C. Z., Chan, M. A., Nagano, K., Pan, B., De\u00a0Mello, S., Gallo, O., Guibas, L. J., Tremblay, J., & Khamis, S., et\u00a0al. (2022). Efficient geometry-aware 3d generative adversarial networks. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 16123\u201316133.","DOI":"10.1109\/CVPR52688.2022.01565"},{"key":"2007_CR11","doi-asserted-by":"crossref","unstructured":"Chen, L., Maddox, R. K., Duan, Z., & Xu, C. (2019). Hierarchical cross-modal talking face generation with dynamic pixel-wise loss. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 7832\u20137841.","DOI":"10.1109\/CVPR.2019.00802"},{"key":"2007_CR12","doi-asserted-by":"crossref","unstructured":"Chen, Z., & Liu, Z. (2022). Relighting4d: Neural relightable human from videos. In European conference on computer vision, Springer, pp. 606\u2013623.","DOI":"10.1007\/978-3-031-19781-9_35"},{"key":"2007_CR13","doi-asserted-by":"crossref","unstructured":"Christensen, P. H. (2015). An approximate reflectance profile for efficient subsurface scattering. In ACM SIGGRAPH 2015 Talks, pp. 1\u20131.","DOI":"10.1145\/2775280.2792555"},{"key":"2007_CR14","doi-asserted-by":"crossref","unstructured":"Chung, J. S., & Zisserman, A. (2017). Out of time: Automated lip sync in the wild. In Computer Vision\u2014ACCV 2016 Workshops: ACCV 2016 International Workshops, Taipei, Taiwan, November 20\u201324, 2016, Revised Selected Papers, Part II 13, Springer, pp. 251\u2013263.","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"2007_CR15","doi-asserted-by":"crossref","unstructured":"Chung, J. S., Senior, A., Vinyals, O., & Zisserman, A. (2017). Lip reading sentences in the wild. In IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2017.367"},{"key":"2007_CR16","unstructured":"Community, B. O. (2018). Blender: A 3D modelling and rendering package. Blender Foundation, Stichting Blender Foundation, Amsterdam, http:\/\/www.blender.org."},{"key":"2007_CR17","doi-asserted-by":"crossref","unstructured":"Cudeiro, D., Bolkart, T., Laidlaw, C., Ranjan, A., Black, M. J. (2019a). Capture, learning, and synthesis of 3d speaking styles. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 10101\u201310111.","DOI":"10.1109\/CVPR.2019.01034"},{"key":"2007_CR18","doi-asserted-by":"publisher","unstructured":"Cudeiro, D., Bolkart, T., Laidlaw, C., Ranjan, A., & Black, M. J. (2019b). Capture, learning, and synthesis of 3d speaking styles. In 2019 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 10093\u201310103, https:\/\/doi.org\/10.1109\/CVPR.2019.01034.","DOI":"10.1109\/CVPR.2019.01034"},{"key":"2007_CR19","doi-asserted-by":"publisher","unstructured":"Debevec, P., Hawkins, T., Tchou, C., Duiker, H.P., Sarokin, W., & Sagar, M. (2000). Acquiring the reflectance field of a human face. In Proceedings of the 27th annual conference on computer graphics and interactive techniques, ACM Press\/Addison-Wesley Publishing Co., USA, SIGGRAPH \u201900, pp. 145\u2013156, https:\/\/doi.org\/10.1145\/344779.344855.","DOI":"10.1145\/344779.344855"},{"key":"2007_CR20","doi-asserted-by":"crossref","unstructured":"Fan, Y., Lin, Z., Saito, J., Wang, W., & Komura, T. (2022). Faceformer: Speech-driven 3d facial animation with transformers. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR52688.2022.01821"},{"issue":"4","key":"2007_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3450626.3459936","volume":"40","author":"Y Feng","year":"2021","unstructured":"Feng, Y., Feng, H., Black, M. J., & Bolkart, T. (2021). Learning an animatable detailed 3d face model from in-the-wild images. ACM Transactions on Graphics (ToG), 40(4), 1\u201313.","journal-title":"ACM Transactions on Graphics (ToG)"},{"key":"2007_CR22","doi-asserted-by":"crossref","unstructured":"Guo, Y., Chen, K., Liang, S., Liu, Y. J., Bao, H., & Zhang, J. (2021). Ad-nerf: Audio driven neural radiance fields for talking head synthesis. In Proceedings of the IEEE\/CVF international conference on computer vision, pp. 5784\u20135794.","DOI":"10.1109\/ICCV48922.2021.00573"},{"key":"2007_CR23","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"2007_CR24","doi-asserted-by":"crossref","unstructured":"Hess, R. (2013). Blender foundations: The essential guide to learning blender 2.5. Routledge.","DOI":"10.4324\/9780240814315"},{"key":"2007_CR25","doi-asserted-by":"crossref","unstructured":"Hou, A., Zhang, Z., Sarkis, M., Bi, N., Tong, Y., & Liu, X. (2021). Towards high fidelity face relighting with realistic shadows. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 14719\u201314728.","DOI":"10.1109\/CVPR46437.2021.01448"},{"key":"2007_CR26","doi-asserted-by":"crossref","unstructured":"Hou, A., Sarkis, M., Bi, N., Tong, Y., & Liu, X. (2022). Face relighting with geometrically consistent shadows. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 4217\u20134226.","DOI":"10.1109\/CVPR52688.2022.00418"},{"key":"2007_CR27","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J. Y., Zhou, T., & Efros, A. A. (2017). Image-to-image translation with conditional adversarial networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1125\u20131134.","DOI":"10.1109\/CVPR.2017.632"},{"key":"2007_CR28","doi-asserted-by":"crossref","unstructured":"Ji, X., Zhou, H., Wang, K., Wu, W., Loy, C.C., Cao, X., Xu, F. (2021). Audio-driven emotional video portraits. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 14080\u201314089.","DOI":"10.1109\/CVPR46437.2021.01386"},{"key":"2007_CR29","doi-asserted-by":"publisher","unstructured":"Karras, T., Aila, T., Laine, S., Herva, A., & Lehtinen, J. (2017). Audio-driven facial animation by joint end-to-end learning of pose and emotion. ACM Trans Graph, 36(4), https:\/\/doi.org\/10.1145\/3072959.3073658.","DOI":"10.1145\/3072959.3073658"},{"issue":"4","key":"2007_CR30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3197517.3201283","volume":"37","author":"H Kim","year":"2018","unstructured":"Kim, H., Garrido, P., Tewari, A., Xu, W., Thies, J., Niessner, M., P\u00e9rez, P., Richardt, C., Zollh\u00f6fer, M., & Theobalt, C. (2018). Deep video portraits. ACM Transactions on Graphics (TOG), 37(4), 1\u201314.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"2007_CR31","doi-asserted-by":"crossref","unstructured":"Li, T., Bolkart, T., Black, M. J., Li, H., & Romero, J. (2017). Learning a model of facial shape and expression from 4d scans. ACM Trans Graph, 36(6), 194-1.","DOI":"10.1145\/3130800.3130813"},{"key":"2007_CR32","doi-asserted-by":"crossref","unstructured":"Liu, X., Xu, Y., Wu, Q., Zhou, H., Wu, W., & Zhou, B. (2022). Semantic-aware implicit neural audio-driven video portrait generation. arXiv preprint arXiv:2201.07786.","DOI":"10.1007\/978-3-031-19836-6_7"},{"key":"2007_CR33","doi-asserted-by":"publisher","unstructured":"Liu, Y., Li, Y., You, S., & Lu, F. (2019). Unsupervised learning for intrinsic image decomposition from a single image. https:\/\/doi.org\/10.48550\/ARXIV.1911.09930.","DOI":"10.48550\/ARXIV.1911.09930"},{"key":"2007_CR34","doi-asserted-by":"crossref","unstructured":"Mildenhall, B., Srinivasan, P.P., Tancik, M., Barron, J.T., Ramamoorthi, R., & Ng, R. (2020). NeRF: Representing scenes as neural radiance fields for view synthesis. arXiv:2003.08934 [cs] version: 2.","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"2007_CR35","doi-asserted-by":"crossref","unstructured":"Nestmeyer, T., Lalonde, J. F., Matthews, I. & Lehrmann, A. (2020). Learning physics-guided face relighting under directional light. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 5124\u20135133.","DOI":"10.1109\/CVPR42600.2020.00517"},{"key":"2007_CR36","doi-asserted-by":"crossref","unstructured":"Or-El, R., Luo, X., Shan, M., Shechtman, E., Park, J. J. & Kemelmacher-Shlizerman, I. (2022). Stylesdf: High-resolution 3d-consistent image and geometry generation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 13503\u201313513.","DOI":"10.1109\/CVPR52688.2022.01314"},{"key":"2007_CR37","unstructured":"Pan, X., Dai, B., Liu, Z., Loy, CC. & Luo, P. (2020). Do 2D gans know 3d shape? Unsupervised 3D shape reconstruction from 2d image gans. arXiv preprint arXiv:2011.00844."},{"issue":"4","key":"2007_CR38","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3450626.3459872","volume":"40","author":"R Pandey","year":"2021","unstructured":"Pandey, R., Escolano, S. O., Legendre, C., Haene, C., Bouaziz, S., Rhemann, C., Debevec, P., & Fanello, S. (2021). Total relighting: Learning to relight portraits for background replacement. ACM Transactions on Graphics (TOG), 40(4), 1\u201321.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"2007_CR39","doi-asserted-by":"crossref","unstructured":"Parkhi, O. M., Vedaldi, A., & Zisserman, A. (2015). Deep face recognition. In British Machine vision conference.","DOI":"10.5244\/C.29.41"},{"key":"2007_CR40","doi-asserted-by":"crossref","unstructured":"Prajwal, K., Mukhopadhyay, R., Namboodiri, V.P., & Jawahar, C. (2020). A lip sync expert is all you need for speech to lip generation in the wild. In Proceedings of the 28th ACM international conference on multimedia, pp. 484\u2013492.","DOI":"10.1145\/3394171.3413532"},{"issue":"10","key":"2007_CR41","doi-asserted-by":"publisher","first-page":"2448","DOI":"10.1364\/JOSAA.18.002448","volume":"18","author":"R Ramamoorthi","year":"2001","unstructured":"Ramamoorthi, R., & Hanrahan, P. (2001). On the relationship between radiance and irradiance: determining the illumination from images of a convex lambertian object. JOSA A, 18(10), 2448\u20132459.","journal-title":"JOSA A"},{"key":"2007_CR42","doi-asserted-by":"publisher","unstructured":"Richard, A., Zollh\u00f6fer, M., Wen, Y., de\u00a0la Torre, F., & Sheikh, Y. (2021). Meshtalk: 3d face animation from speech using cross-modality disentanglement. In 2021 IEEE\/CVF International conference on computer vision (ICCV), pp. 1153\u20131162, https:\/\/doi.org\/10.1109\/ICCV48922.2021.00121.","DOI":"10.1109\/ICCV48922.2021.00121"},{"key":"2007_CR43","doi-asserted-by":"crossref","unstructured":"Schroff, F., Kalenichenko, D., & Philbin, J. (2015). Facenet: A unified embedding for face recognition and clustering. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 815\u2013823.","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"2007_CR44","doi-asserted-by":"crossref","unstructured":"Shen, S., Li, W., Zhu, Z., Duan, Y., Zhou, J., & Lu, J. (2022). Learning dynamic facial radiance fields for few-shot talking head synthesis. In European conference on computer vision.","DOI":"10.1007\/978-3-031-19775-8_39"},{"key":"2007_CR45","doi-asserted-by":"crossref","unstructured":"Shu, Z., Yumer, E., Hadap, S., Sunkavalli, K., Shechtman, E., & Samaras, D. (2017). Neural face editing with intrinsic image disentangling. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 5541\u20135550.","DOI":"10.1109\/CVPR.2017.578"},{"key":"2007_CR46","doi-asserted-by":"publisher","first-page":"585","DOI":"10.1109\/TIFS.2022.3146783","volume":"17","author":"L Song","year":"2022","unstructured":"Song, L., Wu, W., Qian, C., He, R., & Loy, C. C. (2022). Everybody\u2019s talkin\u2019: Let me talk as you want. IEEE Transactions on Information Forensics and Security, 17, 585\u2013598.","journal-title":"IEEE Transactions on Information Forensics and Security"},{"key":"2007_CR47","doi-asserted-by":"crossref","unstructured":"Srinivasan, P. P., Deng, B., Zhang, X., Tancik, M., Mildenhall, B., & Barron, J. T. (2021). Nerv: Neural reflectance and visibility fields for relighting and view synthesis. In CVPR.","DOI":"10.1109\/CVPR46437.2021.00741"},{"key":"2007_CR48","doi-asserted-by":"crossref","unstructured":"Sun, J., Wang, X., Zhang, Y., Li, X., Zhang, Q., Liu, Y., & Wang, J. (2022). Fenerf: Face editing in neural radiance fields. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 7672\u20137682.","DOI":"10.1109\/CVPR52688.2022.00752"},{"key":"2007_CR49","doi-asserted-by":"crossref","unstructured":"Sun, T., Barron, J. T., Tsai, Y. T., Xu, Z., Yu, X., Fyffe, G., Rhemann, C., Busch, J., Debevec, P. E., & Ramamoorthi, R. (2019). Single image portrait relighting. ACM Transactions on Graphics (TOG), 38(4), 79-1.","DOI":"10.1145\/3306346.3323008"},{"issue":"4","key":"2007_CR50","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3072959.3073640","volume":"36","author":"S Suwajanakorn","year":"2017","unstructured":"Suwajanakorn, S., Seitz, S. M., & Kemelmacher-Shlizerman, I. (2017). Synthesizing obama: Learning lip sync from audio. ACM Transactions on Graphics (ToG), 36(4), 1\u201313.","journal-title":"ACM Transactions on Graphics (ToG)"},{"key":"2007_CR51","unstructured":"Tang, J., Wang, K., Zhou, H., Chen, X., He, D., Hu, T., Liu, J., Zeng, G., & Wang J. (2022). Real-time neural radiance talking portrait synthesis via audio-spatial decomposition. arXiv preprint arXiv:2211.12368"},{"issue":"4","key":"2007_CR52","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3072959.3073699","volume":"36","author":"S Taylor","year":"2017","unstructured":"Taylor, S., Kim, T., Yue, Y., Mahler, M., Krahe, J., Rodriguez, A. G., Hodgins, J., & Matthews, I. (2017). A deep learning approach for generalized speech animation. ACM Transactions on Graphics (TOG), 36(4), 1\u201311.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"2007_CR53","doi-asserted-by":"crossref","unstructured":"Thies, J., Elgharib, M., Tewari, A., Theobalt, C., & Nie\u00dfner, M. (2020). Neural voice puppetry: Audio-driven facial reenactment. In European conference on computer vision, Springer, pp. 716\u2013731.","DOI":"10.1007\/978-3-030-58517-4_42"},{"issue":"11","key":"2007_CR54","doi-asserted-by":"publisher","first-page":"1968","DOI":"10.1109\/TPAMI.2008.244","volume":"31","author":"Y Wang","year":"2008","unstructured":"Wang, Y., Zhang, L., Liu, Z., Hua, G., Wen, Z., Zhang, Z., & Samaras, D. (2008). Face relighting from a single image under arbitrary unknown lighting conditions. IEEE Transactions on Pattern Analysis and Machine Intelligence, 31(11), 1968\u20131984.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2007_CR55","doi-asserted-by":"crossref","unstructured":"Wang, Y., Holynski, A., Zhang, X., & Zhang, X. C. (2022). Sunstage: Portrait reconstruction and relighting using the sun as a light stage. arXiv preprint arXiv:2204.03648.","DOI":"10.1109\/CVPR52729.2023.01992"},{"issue":"6","key":"2007_CR56","first-page":"1","volume":"39","author":"Z Wang","year":"2020","unstructured":"Wang, Z., Yu, X., Lu, M., Wang, Q., Qian, C., & Xu, F. (2020). Single image portrait relighting via explicit multiple reflectance channel modeling. ACM Transactions on Graphics (TOG), 39(6), 1\u201313.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"2007_CR57","doi-asserted-by":"crossref","unstructured":"Wu, H., Jia, J., Wang, H., Dou, Y., Duan, C., & Deng, Q. (2021). Imitating arbitrary talking style for realistic audio-driven talking face synthesis. In Proceedings of the 29th ACM international conference on multimedia, pp. 1478\u20131486.","DOI":"10.1145\/3474085.3475280"},{"key":"2007_CR58","doi-asserted-by":"crossref","unstructured":"Xu, Y., Peng, S., Yang, C., Shen, Y., & Zhou, B. (2022). 3d-aware image synthesis via learning structural and textural representations. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 18430\u201318439.","DOI":"10.1109\/CVPR52688.2022.01788"},{"key":"2007_CR59","doi-asserted-by":"crossref","unstructured":"Yang, H., Zhu, H., Wang, Y., Huang, M., Shen, Q., Yang, R., & Cao, X. (2020). Facescape: A large-scale high quality 3d face dataset and detailed riggable 3d face prediction. In IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR42600.2020.00068"},{"key":"2007_CR60","unstructured":"Yao, S., Zhong, R., Yan, Y., Zhai, G., & Yang, X. (2022). DFA-NeRF: Personalized talking head generation via disentangled face attributes neural rendering. arXiv:2201.00791 [cs]."},{"key":"2007_CR61","doi-asserted-by":"crossref","unstructured":"Yeh, Y. Y., Nagano, K., Khamis, S., Kautz, J., Liu, M. Y., Wang, T. C. (2022). Learning to relight portrait images via a virtual light stage and synthetic-to-real adaptation. arXiv preprint arXiv:2209.10510.","DOI":"10.1145\/3550454.3555442"},{"key":"2007_CR62","unstructured":"Yi, R., Ye, Z., Zhang, J., Bao, H., & Liu, Y. J. (2020). Audio-driven talking face video generation with learning-based personalized head pose. arXiv preprint arXiv:2002.10137."},{"key":"2007_CR63","unstructured":"Zhang, H., Goodfellow, I., Metaxas, D., & Odena, A. (2019). Self-attention generative adversarial networks. In International conference on machine learning, pp. 7354\u20137363."},{"key":"2007_CR64","doi-asserted-by":"crossref","unstructured":"Zhang, L., Zhang, Q., Wu, M., Yu, J., & Xu, L. (2021a). Neural video portrait relighting in real-time via consistency modeling. In Proceedings of the IEEE\/CVF international conference on computer vision, pp. 802\u2013812.","DOI":"10.1109\/ICCV48922.2021.00084"},{"key":"2007_CR65","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A. A., Shechtman, E., & Wang, O. (2018). The unreasonable effectiveness of deep features as a perceptual metric. In CVPR.","DOI":"10.1109\/CVPR.2018.00068"},{"issue":"6","key":"2007_CR66","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3478513.3480500","volume":"40","author":"X Zhang","year":"2021","unstructured":"Zhang, X., Srinivasan, P. P., Deng, B., Debevec, P., Freeman, W. T., & Barron, J. T. (2021). Nerfactor: Neural factorization of shape and reflectance under an unknown illumination. ACM Transactions on Graphics (TOG), 40(6), 1\u201318.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"2007_CR67","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Li, L., Ding, Y., & Fan, C. (2021c). Flow-guided one-shot talking face generation with a high-resolution audio-visual dataset. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 3661\u20133670.","DOI":"10.1109\/CVPR46437.2021.00366"},{"key":"2007_CR68","doi-asserted-by":"crossref","unstructured":"Zhao, X., Ma, F., G\u00fcera, D., Ren, Z., Schwing, A. G., & Colburn, A. (2022). Generative multiplane images: Making a 2d gan 3d-aware. In European conference on computer vision, Springer, pp. 18\u201335.","DOI":"10.1007\/978-3-031-20065-6_2"},{"key":"2007_CR69","doi-asserted-by":"crossref","unstructured":"Zheng, Y., Abrevaya, V. F., B\u00fchler, M. C., Chen, X., Black, M. J., & Hilliges, O. (2022). Im avatar: Implicit morphable head avatars from videos. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 13545\u201313555.","DOI":"10.1109\/CVPR52688.2022.01318"},{"key":"2007_CR70","doi-asserted-by":"crossref","unstructured":"Zhou, H., Hadap, S., Sunkavalli, K., Jacobs, D. W. (2019a). Deep single-image portrait relighting. In Proceedings of the IEEE\/CVF international conference on computer vision, pp. 7194\u20137202.","DOI":"10.1109\/ICCV.2019.00729"},{"key":"2007_CR71","doi-asserted-by":"publisher","first-page":"9299","DOI":"10.1609\/aaai.v33i01.33019299","volume":"33","author":"H Zhou","year":"2019","unstructured":"Zhou, H., Liu, Y., Liu, Z., Luo, P., & Wang, X. (2019). Talking face generation by adversarially disentangled audio-visual representation. Proceedings of the AAAI Conference on Artificial Intelligence, 33, 9299\u20139306.","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"2007_CR72","doi-asserted-by":"crossref","unstructured":"Zhou, H., Sun, Y., Wu, W., Loy, C.C., Wang, X., & Liu, Z. (2021). Pose-controllable talking face generation by implicitly modularized audio-visual representation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 4176\u20134186.","DOI":"10.1109\/CVPR46437.2021.00416"},{"issue":"6","key":"2007_CR73","first-page":"1","volume":"39","author":"Y Zhou","year":"2020","unstructured":"Zhou, Y., Han, X., Shechtman, E., Echevarria, J., Kalogerakis, E., & Li, D. (2020). Makelttalk: Speaker-aware talking-head animation. ACM Transactions on Graphics (TOG), 39(6), 1\u201315.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"2007_CR74","unstructured":"Zhu, H., Yang, H., Guo, L., Zhang, Y., Wang, Y., Huang, M., Shen, Q., Yang, R., & Cao, X. (2021). Facescape: 3d facial dataset and benchmark for single-view 3d face reconstruction. arXiv preprint arXiv:2111.01082."}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02007-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-024-02007-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02007-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T14:07:54Z","timestamp":1720706874000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-024-02007-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,16]]},"references-count":74,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2024,8]]}},"alternative-id":["2007"],"URL":"https:\/\/doi.org\/10.1007\/s11263-024-02007-9","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,16]]},"assertion":[{"value":"1 August 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 January 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 February 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}