{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:11:03Z","timestamp":1784268663610,"version":"3.55.0"},"reference-count":62,"publisher":"Association for Computing Machinery (ACM)","issue":"6","license":[{"start":{"date-parts":[[2022,11,30]],"date-time":"2022-11-30T00:00:00Z","timestamp":1669766400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100006754","name":"U.S. Army Research Laboratory","doi-asserted-by":"crossref","award":["W911NF-14-D-0005"],"award-info":[{"award-number":["W911NF-14-D-0005"]}],"id":[{"id":"10.13039\/100006754","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100006754","name":"U.S. Army Research Laboratory","doi-asserted-by":"crossref","award":["W911NF-20-2-0053"],"award-info":[{"award-number":["W911NF-20-2-0053"]}],"id":[{"id":"10.13039\/100006754","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Graph."],"published-print":{"date-parts":[[2022,12]]},"abstract":"<jats:p>\n            We present\n            <jats:bold>Re<\/jats:bold>\n            current\n            <jats:bold>F<\/jats:bold>\n            eature\n            <jats:bold>A<\/jats:bold>\n            lignment (ReFA), an end-to-end neural network for the very rapid creation of production-grade face assets from multi-view images. ReFA is on par with the industrial pipelines in quality for producing accurate, complete, registered, and textured assets directly applicable to physically-based rendering, but produces the asset end-to-end, fully automatically at a significantly faster speed at 4.5 FPS, which is unprecedented among neural-based techniques. Our method represents face geometry as a position map in the UV space. The network first extracts per-pixel features in both the multi-view image space and the UV space. A recurrent module then iteratively optimizes the geometry by projecting the image-space features to the UV space and comparing them with a reference UV-space feature. The optimized geometry then provides pixel-aligned signals for the inference of high-resolution textures. Experiments have validated that ReFA achieves a median error of 0.603\n            <jats:italic>mm<\/jats:italic>\n            in geometry reconstruction, is robust to extreme pose and expression, and excels in sparse-view settings. We believe that the progress achieved by our network enables lightweight, fast face assets acquisition that significantly boosts the downstream applications, such as avatar creation and facial performance capture. It will also enable massive database capturing for deep learning purposes.\n          <\/jats:p>","DOI":"10.1145\/3550454.3555509","type":"journal-article","created":{"date-parts":[[2022,11,30]],"date-time":"2022-11-30T21:19:07Z","timestamp":1669843147000},"page":"1-17","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Rapid Face Asset Acquisition with Recurrent Feature Alignment"],"prefix":"10.1145","volume":"41","author":[{"given":"Shichen","family":"Liu","sequence":"first","affiliation":[{"name":"University of Southern California"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunxuan","family":"Cai","sequence":"additional","affiliation":[{"name":"USC Institute for Creative Technologies"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haiwei","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Southern California"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yichao","family":"Zhou","sequence":"additional","affiliation":[{"name":"University of California Berkeley"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yajie","family":"Zhao","sequence":"additional","affiliation":[{"name":"USC Institute for Creative Technologies"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,11,30]]},"reference":[{"key":"e_1_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1561\/9781680830798"},{"key":"e_1_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/AFGR.2008.4813376"},{"key":"e_1_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00589"},{"key":"e_1_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01197-x"},{"key":"e_1_2_2_5_1","volume-title":"Gross","author":"Beeler Thabo","year":"2010","unstructured":"Thabo Beeler, Bernd Bickel, Paul A. Beardsley, Bob Sumner, and Markus H. Gross. 2010. High-quality single-shot capture of facial geometry. In ACM Transactions on Graphics (TOG)."},{"key":"e_1_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/1964921.1964970"},{"key":"e_1_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/311535.311556"},{"key":"e_1_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2003.1227983"},{"key":"e_1_2_2_9_1","first-page":"1","article-title":"Patchmatch stereo-stereo matching with slanted support windows","volume":"11","author":"Bleyer Michael","year":"2011","unstructured":"Michael Bleyer, Christoph Rhemann, and Carsten Rother. 2011. Patchmatch stereo-stereo matching with slanted support windows.. In Bmvc, Vol. 11. 1--11.","journal-title":"Bmvc"},{"key":"e_1_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.411"},{"key":"e_1_2_2_11_1","doi-asserted-by":"crossref","unstructured":"George Borshukov Dan Piponi Oystein Larsen John P Lewis and Christina Tempelaar-Lietz. 2005. Universal capture-image-based facial animation for\" The Matrix Reloaded\". In ACM Siggraph 2005 Courses. 16--es.","DOI":"10.1145\/1198555.1198596"},{"key":"e_1_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00567"},{"key":"e_1_2_2_13_1","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision. 9429--9439","author":"Chen Anpei","year":"2019","unstructured":"Anpei Chen, Zhang Chen, Guli Zhang, Kenny Mitchell, and Jingyi Yu. 2019. Photorealistic facial details synthesis from single image. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 9429--9439."},{"key":"e_1_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"e_1_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/344779.344855"},{"key":"e_1_2_2_16_1","volume-title":"Friesen","author":"Ekman Paul","year":"1978","unstructured":"Paul Ekman and Wallace V. Friesen. 1978. Facial action coding system: a technique for the measurement of facial movement. In Consulting Psychologists Press."},{"key":"e_1_2_2_17_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3450626.3459936","article-title":"Learning an animatable detailed 3D face model from in-the-wild images","volume":"40","author":"Feng Yao","year":"2021","unstructured":"Yao Feng, Haiwen Feng, Michael J Black, and Timo Bolkart. 2021. Learning an animatable detailed 3D face model from in-the-wild images. ACM Transactions on Graphics (TOG) 40, 4 (2021), 1--13.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"e_1_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_33"},{"key":"e_1_2_2_19_1","volume-title":"Computer Graphics Forum","author":"Fyffe Graham","unstructured":"Graham Fyffe, Koki Nagano, Loc Huynh, Shunsuke Saito, Jay Busch, Andrew Jones, Hao Li, and Paul Debevec. 2017. Multi-View Stereo on Consistent Face Topology. In Computer Graphics Forum, Vol. 36. Wiley Online Library, 295--309."},{"key":"e_1_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383245"},{"key":"e_1_2_2_21_1","first-page":"1","article-title":"Reconstruction of personalized 3D face rigs from monocular video","volume":"35","author":"Garrido Pablo","year":"2016","unstructured":"Pablo Garrido, Michael Zollh\u00f6fer, Dan Casas, Levi Valgaerts, Kiran Varanasi, Patrick P\u00e9rez, and Christian Theobalt. 2016. Reconstruction of personalized 3D face rigs from monocular video. ACM Transactions on Graphics (TOG) 35, 3 (2016), 1--15.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"e_1_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00874"},{"key":"e_1_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2024156.2024163"},{"key":"e_1_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2070781.2024163"},{"key":"e_1_2_2_25_1","volume-title":"Computer Graphics Forum","author":"Graham Paul","unstructured":"Paul Graham, Borom Tunwattanapong, Jay Busch, Xueming Yu, Andrew Jones, Paul Debevec, and Abhijeet Ghosh. 2013. Measurement-based synthesis of facial micro-geometry. In Computer Graphics Forum, Vol. 32. Wiley Online Library, 335--344."},{"key":"e_1_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00257"},{"key":"e_1_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00298"},{"key":"e_1_2_2_29_1","volume-title":"DPSNet: End-to-end Deep Plane Sweep Stereo. In International Conference on Learning Representations.","author":"Im Sunghoon","year":"2018","unstructured":"Sunghoon Im, Hae-Gon Jeon, Stephen Lin, and In So Kweon. 2018. DPSNet: End-to-end Deep Plane Sweep Stereo. In International Conference on Learning Representations."},{"key":"e_1_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2001.990462"},{"key":"e_1_2_2_31_1","volume-title":"Realistic Human Eye","author":"Kollar Andor","unstructured":"Andor Kollar. 2019. Realistic Human Eye. http:\/\/kollarandor.com\/gallery\/3d-human-eye\/. Online; Accessed: 2022-3-30."},{"key":"e_1_2_2_32_1","volume-title":"Farid Boussaid, and Mohammed Bennamoun.","author":"Laga Hamid","year":"2020","unstructured":"Hamid Laga, Laurent Valentin Jospin, Farid Boussaid, and Mohammed Bennamoun. 2020. A survey on deep learning techniques for stereo-based depth estimation. IEEE Transactions on Pattern Analysis and Machine Intelligence (2020)."},{"key":"e_1_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00084"},{"key":"e_1_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3230744.3230778"},{"key":"e_1_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2009.03.011"},{"key":"e_1_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/1618452.1618521"},{"key":"e_1_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417817"},{"key":"e_1_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00347"},{"key":"e_1_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00380"},{"key":"e_1_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01262"},{"key":"e_1_2_2_41_1","volume-title":"Debevec","author":"Ma Wan-Chun","year":"2007","unstructured":"Wan-Chun Ma, Tim Hawkins, Pieter Peers, Charles-F\u00e9lix Chabert, Malte Weiss, and Paul E. Debevec. 2007. Rapid Acquisition of Specular and Diffuse Normal Maps from Polarized Spherical Gradient Illumination. In Rendering Techniques."},{"key":"e_1_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/1401032.1401036"},{"key":"e_1_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530127"},{"key":"e_1_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"e_1_2_2_45_1","volume-title":"3D face reconstruction by learning from synthetic data. In 2016 fourth international conference on 3D vision (3DV)","author":"Richardson Elad","unstructured":"Elad Richardson, Matan Sela, and Ron Kimmel. 2016. 3D face reconstruction by learning from synthetic data. In 2016 fourth international conference on 3D vision (3DV). IEEE, 460--469."},{"key":"e_1_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.589"},{"key":"e_1_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00795"},{"key":"e_1_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_31"},{"key":"e_1_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/1057432.1057456"},{"key":"e_1_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.78"},{"key":"e_1_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"e_1_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00270"},{"key":"e_1_2_2_53_1","volume-title":"Proceedings of the IEEE International Conference on Computer Vision Workshops. 1274--1283","author":"Tewari Ayush","year":"2017","unstructured":"Ayush Tewari, Michael Zollhofer, Hyeongwoo Kim, Pablo Garrido, Florian Bernard, Patrick Perez, and Christian Theobalt. 2017. Mofa: Model-based deep convolutional face autoencoder for unsupervised monocular reconstruction. In Proceedings of the IEEE International Conference on Computer Vision Workshops. 1274--1283."},{"key":"e_1_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/2929464.2929475"},{"key":"e_1_2_2_55_1","volume-title":"Triplegangers Face Models. https:\/\/triplegangers.com\/. Online","year":"2021","unstructured":"Triplegangers. 2021. Triplegangers Face Models. https:\/\/triplegangers.com\/. Online; Accessed: 2021-12-05."},{"key":"e_1_2_2_56_1","article-title":"Visualizing data using t-SNE","volume":"9","author":"der Maaten Laurens Van","year":"2008","unstructured":"Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of machine learning research 9, 11 (2008).","journal-title":"Journal of machine learning research"},{"key":"e_1_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00917"},{"key":"e_1_2_2_58_1","volume-title":"The European Conference on Computer Vision Workshops (ECCVW).","author":"Wang Xintao","year":"2018","unstructured":"Xintao Wang, Ke Yu, Shixiang Wu, Jinjin Gu, Yihao Liu, Chao Dong, Yu Qiao, and Chen Change Loy. 2018b. ESRGAN: Enhanced super-resolution generative adversarial networks. In The European Conference on Computer Vision Workshops (ECCVW)."},{"key":"e_1_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201364"},{"key":"e_1_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00068"},{"key":"e_1_2_2_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00567"},{"key":"e_1_2_2_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.544"}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3550454.3555509","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3550454.3555509","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:51:43Z","timestamp":1750182703000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3550454.3555509"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,30]]},"references-count":62,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2022,12]]}},"alternative-id":["10.1145\/3550454.3555509"],"URL":"https:\/\/doi.org\/10.1145\/3550454.3555509","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"value":"0730-0301","type":"print"},{"value":"1557-7368","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11,30]]},"assertion":[{"value":"2022-11-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}