{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T10:05:11Z","timestamp":1768989911568,"version":"3.49.0"},"reference-count":61,"publisher":"Association for Computing Machinery (ACM)","issue":"5","license":[{"start":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T00:00:00Z","timestamp":1692576000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Graph."],"published-print":{"date-parts":[[2023,10,31]]},"abstract":"<jats:p>We present a novel method for reconstructing clothed humans from a sparse set of, e.g., 1\u20136 RGB images. Despite impressive results from recent works employing deep implicit representation, we revisit the volumetric approach and demonstrate that better performance can be achieved with proper system design. The volumetric representation offers significant advantages in leveraging 3D spatial context through 3D convolutions, and the notorious quantization error is largely negligible with a reasonably large yet affordable volume resolution, e.g., 512. To handle memory and computation costs, we propose a sophisticated coarse-to-fine strategy with voxel culling and subspace sparse convolution. Our method starts with a discretized visual hull to compute a coarse shape and then focuses on a narrow band nearby the coarse shape for refinement. Once the shape is reconstructed, we adopt an image-based rendering approach, which computes the colors of surface points by blending input images with learned weights. Extensive experimental results show that our method significantly reduces the mean point-to-surface (P2S) precision of state-of-the-art methods by more than 50% to achieve approximately 2mm accuracy with a 512 volume resolution. Additionally, images rendered from our textured model achieve a higher peak signal-to-noise ratio (PSNR) compared to state-of-the-art methods.<\/jats:p>","DOI":"10.1145\/3606032","type":"journal-article","created":{"date-parts":[[2023,7,15]],"date-time":"2023-07-15T09:44:46Z","timestamp":1689414286000},"page":"1-15","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["High-Resolution Volumetric Reconstruction for Clothed Humans"],"prefix":"10.1145","volume":"42","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6943-0074","authenticated-orcid":false,"given":"Sicong","family":"Tang","sequence":"first","affiliation":[{"name":"Simon Fraser University, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2388-0716","authenticated-orcid":false,"given":"Guangyuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Group, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2376-1833","authenticated-orcid":false,"given":"Qing","family":"Ran","sequence":"additional","affiliation":[{"name":"Alibaba Group, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0552-9566","authenticated-orcid":false,"given":"Lingzhi","family":"Li","sequence":"additional","affiliation":[{"name":"Alibaba Group, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2283-4976","authenticated-orcid":false,"given":"Li","family":"Shen","sequence":"additional","affiliation":[{"name":"Alibaba Group, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4506-6973","authenticated-orcid":false,"given":"Ping","family":"Tan","sequence":"additional","affiliation":[{"name":"Simon Fraser University, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,8,21]]},"reference":[{"key":"e_1_3_3_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00238"},{"key":"e_1_3_3_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00156"},{"key":"e_1_3_3_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/1073204.1073207"},{"key":"e_1_3_3_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00552"},{"key":"e_1_3_3_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_34"},{"key":"e_1_3_3_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00609"},{"key":"e_1_3_3_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00700"},{"key":"e_1_3_3_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766945"},{"key":"e_1_3_3_10_1","unstructured":"Blender Online Community. (n.d.). Blender. https:\/\/www.blender.org\/"},{"key":"e_1_3_3_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925969"},{"key":"e_1_3_3_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.602"},{"key":"e_1_3_3_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_35"},{"key":"e_1_3_3_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00961"},{"key":"e_1_3_3_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356571"},{"key":"e_1_3_3_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01114"},{"key":"e_1_3_3_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01086"},{"key":"e_1_3_3_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00060"},{"key":"e_1_3_3_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00055"},{"key":"e_1_3_3_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_21"},{"key":"e_1_3_3_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00316"},{"key":"e_1_3_3_22_1","article-title":"3D human body reconstruction from a single image via volumetric regression","volume":"1809","author":"Jackson Aaron S.","year":"2018","unstructured":"Aaron S. Jackson, Chris Manafas, and Georgios Tzimiropoulos. 2018. 3D human body reconstruction from a single image via volumetric regression. ArXiv abs\/1809.03770 (2018).","journal-title":"ArXiv"},{"key":"e_1_3_3_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00604"},{"key":"e_1_3_3_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2782743"},{"key":"e_1_3_3_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00868"},{"key":"e_1_3_3_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00744"},{"key":"e_1_3_3_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00530"},{"key":"e_1_3_3_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00234"},{"key":"e_1_3_3_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_4"},{"key":"e_1_3_3_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00445"},{"key":"e_1_3_3_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"key":"e_1_3_3_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/37402.37422"},{"key":"e_1_3_3_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00459"},{"key":"e_1_3_3_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"e_1_3_3_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298631"},{"key":"e_1_3_3_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR.2011.6092378"},{"key":"e_1_3_3_37_1","doi-asserted-by":"crossref","first-page":"483","DOI":"10.1007\/978-3-319-46484-8_29","volume-title":"Computer Vision \u2013 ECCV 2016","author":"Newell Alejandro","year":"2016","unstructured":"Alejandro Newell, Kaiyu Yang, and Jia Deng. 2016. Stacked hourglass networks for human pose estimation. In Computer Vision \u2013 ECCV 2016, Bastian Leibe, Jiri Matas, Nicu Sebe, and Max Welling (Eds.). Springer International Publishing, Cham, 483\u2013499."},{"key":"e_1_3_3_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2018.00062"},{"key":"e_1_3_3_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00025"},{"key":"e_1_3_3_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"e_1_3_3_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00055"},{"key":"e_1_3_3_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_31"},{"key":"e_1_3_3_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00894"},{"key":"e_1_3_3_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00239"},{"key":"e_1_3_3_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00016"},{"key":"e_1_3_3_46_1","volume-title":"CVPR","author":"Sengupta Soumyadip","year":"2020","unstructured":"Soumyadip Sengupta, Vivek Jayaram, Brian Curless, Steven M. Seitz, and Ira Kemelmacher-Shlizerman. 2020. Background matting: The world is your green screen. In CVPR."},{"key":"e_1_3_3_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01541"},{"key":"e_1_3_3_48_1","volume-title":"ECCV","author":"Shao Ruizhi","year":"2022","unstructured":"Ruizhi Shao, Zerong Zheng, Hongwen Zhang, Jingxiang Sun, and Yebin Liu. 2022b. DiffuStereo: High quality human reconstruction via diffusion-based stereo using sparse cameras. In ECCV."},{"key":"e_1_3_3_49_1","unstructured":"Twindom. (n.d.). Human 3D Body Model Datasets. https:\/\/web.twindom.com\/."},{"key":"e_1_3_3_50_1","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1007\/978-3-030-01234-2_2","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Varol G\u00fcl","year":"2018","unstructured":"G\u00fcl Varol, Duygu Ceylan, Bryan Russell, Jimei Yang, Ersin Yumer, Ivan Laptev, and Cordelia Schmid. 2018. BodyNet: Volumetric inference of 3D human body shapes. In Computer Vision \u2013 ECCV 2018, Vittorio Ferrari, Martial Hebert, Cristian Sminchisescu, and Yair Weiss (Eds.). Springer International Publishing, Cham, 20\u201338."},{"key":"e_1_3_3_51_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"e_1_3_3_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/1618452.1618520"},{"key":"e_1_3_3_53_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_54"},{"key":"e_1_3_3_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01294"},{"key":"e_1_3_3_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00785"},{"key":"e_1_3_3_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00455"},{"key":"e_1_3_3_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.104"},{"key":"e_1_3_3_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2928296"},{"key":"e_1_3_3_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00569"},{"key":"e_1_3_3_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00618"},{"key":"e_1_3_3_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3050505"},{"key":"e_1_3_3_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00783"}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3606032","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3606032","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:36:20Z","timestamp":1750178180000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3606032"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,21]]},"references-count":61,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2023,10,31]]}},"alternative-id":["10.1145\/3606032"],"URL":"https:\/\/doi.org\/10.1145\/3606032","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"value":"0730-0301","type":"print"},{"value":"1557-7368","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8,21]]},"assertion":[{"value":"2022-11-06","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-06-17","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-08-21","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}