{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T18:38:17Z","timestamp":1772822297346,"version":"3.50.1"},"reference-count":92,"publisher":"Association for Computing Machinery (ACM)","issue":"6","license":[{"start":{"date-parts":[[2023,12,5]],"date-time":"2023-12-05T00:00:00Z","timestamp":1701734400000},"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":[[2023,12,5]]},"abstract":"<jats:p>High-quality large-scale scene rendering requires a scalable representation and accurate camera poses. This research combines tile-based hybrid neural fields with parallel distributive optimization to improve bundle-adjusting neural radiance fields. The proposed method scales with a divide-and-conquer strategy. We partition scenes into tiles, each with a multi-resolution hash feature grid and shallow chained diffuse and specular multilayer perceptrons (MLPs). Tiles unify foreground and background via a spatial contraction function that allows both distant objects in outdoor scenes and planar reflections as virtual images outside the tile. Decomposing appearance with the specular MLP allows a specular-aware warping loss to provide a second optimization path for camera poses. We apply the alternating direction method of multipliers (ADMM) to achieve consensus among camera poses while maintaining parallel tile optimization. Experimental results show that our method outperforms state-of-the-art neural scene rendering method quality by 5%--10% in PSNR, maintaining sharp distant objects and view-dependent reflections across six indoor and outdoor scenes.<\/jats:p>","DOI":"10.1145\/3618369","type":"journal-article","created":{"date-parts":[[2023,12,5]],"date-time":"2023-12-05T10:20:48Z","timestamp":1701771648000},"page":"1-18","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["ScaNeRF: Scalable Bundle-Adjusting Neural Radiance Fields for Large-Scale Scene Rendering"],"prefix":"10.1145","volume":"42","author":[{"given":"Xiuchao","family":"Wu","sequence":"first","affiliation":[{"name":"State Key Lab of CAD&amp;CG, Zhejiang University, China"}]},{"given":"Jiamin","family":"Xu","sequence":"additional","affiliation":[{"name":"Hangzhou Dianzi University, China"}]},{"given":"Xin","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Lab of CAD&amp;CG, Zhejiang University, China"}]},{"given":"Hujun","family":"Bao","sequence":"additional","affiliation":[{"name":"State Key Lab of CAD&amp;CG, Zhejiang University, China"}]},{"given":"Qixing","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Texas at Austin, USA"}]},{"given":"Yujun","family":"Shen","sequence":"additional","affiliation":[{"name":"Ant Group, China"}]},{"given":"James","family":"Tompkin","sequence":"additional","affiliation":[{"name":"Brown University, USA"}]},{"given":"Weiwei","family":"Xu","sequence":"additional","affiliation":[{"name":"State Key Lab of CAD&amp;CG, Zhejiang University, China"}]}],"member":"320","published-online":{"date-parts":[[2023,12,5]]},"reference":[{"key":"e_1_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15552-9_3"},{"key":"e_1_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00580"},{"key":"e_1_2_2_3_1","volume-title":"Neural reflectance fields for appearance acquisition. arXiv preprint arXiv:2008.03824","author":"Bi Sai","year":"2020","unstructured":"Sai Bi, Zexiang Xu, Pratul Srinivasan, Ben Mildenhall, Kalyan Sunkavalli, Milo\u0161 Ha\u0161an, Yannick Hold-Geoffroy, David Kriegman, and Ravi Ramamoorthi. 2020. Neural reflectance fields for appearance acquisition. arXiv preprint arXiv:2008.03824 (2020)."},{"key":"e_1_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00405"},{"key":"e_1_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01245"},{"key":"e_1_2_2_6_1","doi-asserted-by":"crossref","unstructured":"Stephen Boyd Neal Parikh Eric Chu Borja Peleato Jonathan Eckstein et al. 2011. Distributed optimization and statistical learning via the alternating direction method of multipliers. Foundations and Trends in Machine learning 3 1 (2011) 1--122.","DOI":"10.1561\/2200000016"},{"key":"e_1_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/383259.383309"},{"key":"e_1_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2016.2624754"},{"key":"e_1_2_2_9_1","unstructured":"CapturingReality. 2016. Reality capture http:\/\/capturingreality.com."},{"key":"e_1_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01565"},{"key":"e_1_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_20"},{"key":"e_1_2_2_12_1","volume-title":"Mobilenerf: Exploiting the polygon rasterization pipeline for efficient neural field rendering on mobile architectures. arXiv preprint arXiv:2208.00277","author":"Chen Zhiqin","year":"2022","unstructured":"Zhiqin Chen, Thomas Funkhouser, Peter Hedman, and Andrea Tagliasacchi. 2022a. Mobilenerf: Exploiting the polygon rasterization pipeline for efficient neural field rendering on mobile architectures. arXiv preprint arXiv:2208.00277 (2022)."},{"key":"e_1_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_16"},{"key":"e_1_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00603"},{"key":"e_1_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00603"},{"key":"e_1_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.193"},{"key":"e_1_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01254"},{"key":"e_1_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01061"},{"key":"e_1_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2658577"},{"key":"e_1_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10605-2_54"},{"key":"e_1_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.194"},{"key":"e_1_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00542"},{"key":"e_1_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01408"},{"key":"e_1_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00543"},{"key":"e_1_2_2_25_1","volume-title":"light & material decomposition from images using monte carlo rendering and denoising. arXiv preprint arXiv:2206.03380","author":"Hasselgren Jon","year":"2022","unstructured":"Jon Hasselgren, Nikolai Hofmann, and Jacob Munkberg. 2022. Shape, light & material decomposition from images using monte carlo rendering and denoising. arXiv preprint arXiv:2206.03380 (2022)."},{"key":"e_1_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275084"},{"key":"e_1_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2980179.2982420"},{"key":"e_1_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00582"},{"key":"e_1_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01256"},{"key":"e_1_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00583"},{"key":"e_1_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00579"},{"key":"e_1_2_2_32_1","doi-asserted-by":"crossref","unstructured":"Roland Jung and Stephan Weiss. 2021. Scalable recursive distributed collaborative state estimation for aided inertial navigation. In ICRA. 1896--1902.","DOI":"10.1109\/ICRA48506.2021.9561203"},{"key":"e_1_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008321423879"},{"key":"e_1_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530707"},{"key":"e_1_2_2_35_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417861"},{"key":"e_1_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00569"},{"key":"e_1_2_2_38_1","unstructured":"Yunzhi Lin Thomas M\u00fcller Jonathan Tremblay Bowen Wen Stephen Tyree Alex Evans Patricio A. Vela and Stan Birchfield. 2023. Parallel Inversion of Neural Radiance Fields for Robust Pose Estimation. In ICRA."},{"key":"e_1_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00593"},{"key":"e_1_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356495"},{"key":"e_1_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00780"},{"key":"e_1_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01587"},{"key":"e_1_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"e_1_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530127"},{"key":"e_1_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00810"},{"key":"e_1_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/1027411.1027414"},{"key":"e_1_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00540"},{"key":"e_1_2_2_48_1","volume-title":"Adv. Neural Inform. Process. Syst.","volume":"32","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. 2019. Pytorch: An imperative style, high-performance deep learning library. In Adv. Neural Inform. Process. Syst., Vol. 32."},{"key":"e_1_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1137\/15M1024950"},{"key":"e_1_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_9"},{"key":"e_1_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01407"},{"key":"e_1_2_2_52_1","volume-title":"Merf: Memory-efficient radiance fields for real-time view synthesis in unbounded scenes. arXiv preprint arXiv:2302.12249","author":"Reiser Christian","year":"2023","unstructured":"Christian Reiser, Richard Szeliski, Dor Verbin, Pratul P Srinivasan, Ben Mildenhall, Andreas Geiger, Jonathan T Barron, and Peter Hedman. 2023. Merf: Memory-efficient radiance fields for real-time view synthesis in unbounded scenes. arXiv preprint arXiv:2302.12249 (2023)."},{"key":"e_1_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01259"},{"key":"e_1_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01204"},{"key":"e_1_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3384535"},{"key":"e_1_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01255"},{"key":"e_1_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00326"},{"key":"e_1_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.445"},{"key":"e_1_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/2185520.2185596"},{"key":"e_1_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/882262.882281"},{"key":"e_1_2_2_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00741"},{"key":"e_1_2_2_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00538"},{"key":"e_1_2_2_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530718"},{"key":"e_1_2_2_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00807"},{"key":"e_1_2_2_65_1","volume-title":"Nerfstudio: A Modular Framework for Neural Radiance Field Development. In SIGGRAPH Conference Proceedings.","author":"Tancik Matthew","year":"2023","unstructured":"Matthew Tancik, Ethan Weber, Evonne Ng, Ruilong Li, Brent Yi, Justin Kerr, Terrance Wang, Alexander Kristoffersen, Jake Austin, Kamyar Salahi, Abhik Ahuja, David McAllister, and Angjoo Kanazawa. 2023. Nerfstudio: A Modular Framework for Neural Radiance Field Development. In SIGGRAPH Conference Proceedings."},{"key":"e_1_2_2_66_1","volume-title":"Int. Conf. Learn. Represent.","author":"Tang Chengzhou","year":"2018","unstructured":"Chengzhou Tang and Ping Tan. 2018. Ba-net: Dense bundle adjustment network. In Int. Conf. Learn. Represent."},{"key":"e_1_2_2_67_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44480-7_21"},{"key":"e_1_2_2_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01258"},{"key":"e_1_2_2_69_1","volume-title":"SUDS: Scalable Urban Dynamic Scenes. arXiv preprint arXiv:2303.14536","author":"Turki Haithem","year":"2023","unstructured":"Haithem Turki, Jason Y Zhang, Francesco Ferroni, and Deva Ramanan. 2023. SUDS: Scalable Urban Dynamic Scenes. arXiv preprint arXiv:2303.14536 (2023)."},{"key":"e_1_2_2_70_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00541"},{"key":"e_1_2_2_71_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_9"},{"key":"e_1_2_2_72_1","first-page":"600","article-title":"Image quality assessment: from error visibility to structural similarity","volume":"13","author":"Wang Zhou","year":"2004","unstructured":"Zhou Wang, Alan C Bovik, Hamid R Sheikh, and Eero P Simoncelli. 2004. Image quality assessment: from error visibility to structural similarity. IEEE TIP 13, 4 (2004), 600--612.","journal-title":"IEEE TIP"},{"key":"e_1_2_2_73_1","volume-title":"NeRF-: Neural radiance fields without known camera parameters. arXiv preprint arXiv:2102.07064","author":"Wang Zirui","year":"2021","unstructured":"Zirui Wang, Shangzhe Wu, Weidi Xie, Min Chen, and Victor Adrian Prisacariu. 2021. NeRF-: Neural radiance fields without known camera parameters. arXiv preprint arXiv:2102.07064 (2021)."},{"key":"e_1_2_2_74_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00843"},{"key":"e_1_2_2_75_1","doi-asserted-by":"publisher","DOI":"10.1145\/344779.344925"},{"key":"e_1_2_2_76_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530153"},{"key":"e_1_2_2_77_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_7"},{"key":"e_1_2_2_78_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14505"},{"key":"e_1_2_2_79_1","volume-title":"Grid-guided Neural Radiance Fields for Large Urban Scenes. arXiv preprint arXiv:2303.14001","author":"Xu Linning","year":"2023","unstructured":"Linning Xu, Yuanbo Xiangli, Sida Peng, Xingang Pan, Nanxuan Zhao, Christian Theobalt, Bo Dai, and Dahua Lin. 2023. Grid-guided Neural Radiance Fields for Large Urban Scenes. arXiv preprint arXiv:2303.14001 (2023)."},{"key":"e_1_2_2_80_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00536"},{"key":"e_1_2_2_81_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19821-2_40"},{"key":"e_1_2_2_82_1","doi-asserted-by":"crossref","unstructured":"Lin Yen-Chen Pete Florence Jonathan T Barron Alberto Rodriguez Phillip Isola and Tsung-Yi Lin. 2021. inerf: Inverting neural radiance fields for pose estimation. In IROS. 1323--1330.","DOI":"10.1109\/IROS51168.2021.9636708"},{"key":"e_1_2_2_83_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00570"},{"key":"e_1_2_2_84_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00455"},{"key":"e_1_2_2_85_1","volume-title":"Monosdf: Exploring monocular geometric cues for neural implicit surface reconstruction. arXiv preprint arXiv:2206.00665","author":"Yu Zehao","year":"2022","unstructured":"Zehao Yu, Songyou Peng, Michael Niemeyer, Torsten Sattler, and Andreas Geiger. 2022. Monosdf: Exploring monocular geometric cues for neural implicit surface reconstruction. arXiv preprint arXiv:2206.00665 (2022)."},{"key":"e_1_2_2_86_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00541"},{"key":"e_1_2_2_87_1","volume-title":"Analyzing and improving neural radiance fields. arXiv preprint arXiv:2010.07492","author":"Zhang Kai","year":"2020","unstructured":"Kai Zhang, Gerrot Riegler, Noah Snavely, and Vladlen Koltun. 2020. Nerf++: Analyzing and improving neural radiance fields. arXiv preprint arXiv:2010.07492 (2020)."},{"key":"e_1_2_2_88_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.13"},{"key":"e_1_2_2_89_1","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480500"},{"key":"e_1_2_2_90_1","volume-title":"Efficient large-scale scene representation with a hybrid of high-resolution grid and plane features. arXiv preprint arXiv:2303.03003","author":"Zhang Yuqi","year":"2023","unstructured":"Yuqi Zhang, Guanying Chen, and Shuguang Cui. 2023. Efficient large-scale scene representation with a hybrid of high-resolution grid and plane features. arXiv preprint arXiv:2303.03003 (2023)."},{"key":"e_1_2_2_91_1","doi-asserted-by":"crossref","unstructured":"Pengxiang Zhu Patrick Geneva Wei Ren and Guoquan Huang. 2021. Distributed visual-inertial cooperative localization. In IROS. 8714--8721.","DOI":"10.1109\/IROS51168.2021.9636031"},{"key":"e_1_2_2_92_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01245"}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3618369","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3618369","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T10:45:59Z","timestamp":1755773159000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3618369"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,5]]},"references-count":92,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2023,12,5]]}},"alternative-id":["10.1145\/3618369"],"URL":"https:\/\/doi.org\/10.1145\/3618369","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"value":"0730-0301","type":"print"},{"value":"1557-7368","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,5]]},"assertion":[{"value":"2023-12-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}