{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T12:30:06Z","timestamp":1766147406291,"version":"3.48.0"},"reference-count":43,"publisher":"Association for Computing Machinery (ACM)","issue":"2","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Graph."],"published-print":{"date-parts":[[2026,4,30]]},"abstract":"<jats:p>Efficient and scalable 3D surface reconstruction from range data remains a core challenge in computer graphics and vision, particularly in real-time and resource-constrained scenarios. Traditional volumetric methods based on fixed-resolution voxel grids or hierarchical structures like octrees often suffer from memory inefficiency, computational overhead, and a lack of GPU support. We propose a novel variance-adaptive, multi-resolution voxel grid that dynamically adjusts voxel size based on the local variance of signed distance field (SDF) observations. Unlike prior multi-resolution approaches that rely on recursive octree structures, our method leverages a flat spatial hash table to store all voxel blocks, supporting constant-time access and full GPU parallelism. This design enables high memory efficiency and real-time scalability. We further demonstrate how our representation supports GPU-accelerated rendering through a parallel quad-tree structure for Gaussian Splatting, enabling effective control over splat density. Our open-source CUDA\/C++ implementation achieves up to 13\u00d7 speedup and 4\u00d7 lower memory usage compared with fixed-resolution baselines, while maintaining on par results in terms of reconstruction accuracy, offering a practical and extensible solution for high-performance 3D reconstruction.<\/jats:p>","DOI":"10.1145\/3777909","type":"journal-article","created":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T11:21:19Z","timestamp":1763637679000},"page":"1-15","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Resolution Where It Counts: Hash-based GPU-Accelerated 3D Reconstruction via Variance-Adaptive Voxel Grids"],"prefix":"10.1145","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-3369-9456","authenticated-orcid":false,"given":"Lorenzo","family":"De Rebotti","sequence":"first","affiliation":[{"name":"University of Rome La Sapienza","place":["Rome, Italy"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3569-4191","authenticated-orcid":false,"given":"Emanuele","family":"Giacomini","sequence":"additional","affiliation":[{"name":"University of Rome La Sapienza","place":["Rome, Italy"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8038-9989","authenticated-orcid":false,"given":"Giorgio","family":"Grisetti","sequence":"additional","affiliation":[{"name":"University of Rome La Sapienza","place":["Rome, Italy"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1332-3496","authenticated-orcid":false,"given":"Luca","family":"Di Giammarino","sequence":"additional","affiliation":[{"name":"University of Rome La Sapienza","place":["Rome, Italy"]}]}],"member":"320","published-online":{"date-parts":[[2025,12,19]]},"reference":[{"key":"e_1_3_1_2_1","doi-asserted-by":"publisher","DOI":"10.2312\/egtp.19871000"},{"key":"e_1_3_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611395"},{"key":"e_1_3_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/237170.237269"},{"key":"e_1_3_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3573628"},{"key":"e_1_3_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"e_1_3_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3054739"},{"key":"e_1_3_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981147"},{"key":"e_1_3_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3281907"},{"key":"e_1_3_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3456509"},{"key":"e_1_3_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3061989"},{"key":"e_1_3_1_12_1","first-page":"27630","volume-title":"Proc. of the IEEE Intl. Conf. on Computer Vision (ICCV)","author":"Giacomini Emanuele","year":"2025","unstructured":"Emanuele Giacomini, Luca Di Giammarino, Lorenzo De Rebotti, Giorgio Grisetti, and Martin R. Oswald. 2025. Splat-LOAM: Gaussian splatting LiDAR odometry and mapping. In Proc. of the IEEE Intl. Conf. on Computer Vision (ICCV). 27630\u201327639."},{"key":"e_1_3_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00425"},{"key":"e_1_3_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02018"},{"issue":"4","key":"e_1_3_1_15_1","article-title":"3d gaussian splatting for real-time radiance field rendering.","volume":"42","author":"Kerbl Bernhard","year":"2023","unstructured":"Bernhard Kerbl, Georgios Kopanas, Thomas Leimk\u00fchler, and George Drettakis. 2023. 3d gaussian splatting for real-time radiance field rendering. ACM Trans. on Graphics 42, 4 (2023), 139\u20131.","journal-title":"ACM Trans. on Graphics"},{"key":"e_1_3_1_16_1","doi-asserted-by":"publisher","DOI":"10.1080\/2151237X.2011.563682"},{"key":"e_1_3_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/37401.37422"},{"key":"e_1_3_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01708"},{"key":"e_1_3_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00459"},{"key":"e_1_3_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530127"},{"issue":"3","key":"e_1_3_1_21_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2487228.2487235","article-title":"VDB: High-resolution sparse volumes with dynamic topology","volume":"32","author":"Museth Ken","year":"2013","unstructured":"Ken Museth. 2013. VDB: High-resolution sparse volumes with dynamic topology. ACM Trans. on Graphics 32, 3 (2013), 1\u201322.","journal-title":"ACM Trans. on Graphics"},{"key":"e_1_3_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450623.3464653"},{"key":"e_1_3_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR.2011.6092378"},{"key":"e_1_3_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2508363.2508374"},{"key":"e_1_3_1_25_1","first-page":"1366","volume-title":"Proc. of the IEEE\/RSJ Intl. Conf. on Intelligent Robots and Systems (IROS)","author":"Oleynikova Helen","year":"2017","unstructured":"Helen Oleynikova, Zachary Taylor, Marius Fehr, Roland Siegwart, and Juan Nieto. 2017. Voxblox: Incremental 3d euclidean signed distance fields for on-board mav planning. In Proc. of the IEEE\/RSJ Intl. Conf. on Intelligent Robots and Systems (IROS). IEEE, 1366\u20131373."},{"key":"e_1_3_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2024.3422055"},{"key":"e_1_3_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657455"},{"key":"e_1_3_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00022"},{"key":"e_1_3_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3396638"},{"key":"e_1_3_1_30_1","unstructured":"Julian Straub Thomas Whelan Lingni Ma Yufan Chen Erik Wijmans Simon Green Jakob J. Engel Raul Mur-Artal Carl Ren Shobhit Verma et\u00a0al. 2019. The Replica Dataset: A Digital Replica of Indoor Spaces. arXiv:1906.05797. Retrieved from https:\/\/arxiv.org\/abs\/1906.05797"},{"key":"e_1_3_1_31_1","doi-asserted-by":"publisher","DOI":"10.1177\/02783649251369905"},{"key":"e_1_3_1_32_1","first-page":"47","volume-title":"Proc. of the Vision, Modeling, and Visualization Workshop (VMV)","author":"Teschner Matthias","year":"2003","unstructured":"Matthias Teschner, Bruno Heidelberger, Matthias M\u00fcller, Danat Pomerantes, and Markus H. Gross. 2003. Optimized spatial hashing for collision detection of deformable objects. In Proc. of the Vision, Modeling, and Visualization Workshop (VMV), Thomas Ertl (Ed.). 47\u201354."},{"key":"e_1_3_1_33_1","first-page":"654","volume-title":"Proc. of the International Conference on 3D Vision (3DV)","author":"Vespa Emanuele","year":"2019","unstructured":"Emanuele Vespa, Nils Funk, Paul H. J. Kelly, and Stefan Leutenegger. 2019. Adaptive-resolution octree-based volumetric SLAM. In Proc. of the International Conference on 3D Vision (3DV). IEEE, 654\u2013662."},{"key":"e_1_3_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2792537"},{"key":"e_1_3_1_35_1","doi-asserted-by":"publisher","DOI":"10.3390\/s22031296"},{"key":"e_1_3_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"e_1_3_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3502065"},{"key":"e_1_3_1_38_1","doi-asserted-by":"publisher","DOI":"10.1080\/00401706.1962.10490022"},{"key":"e_1_3_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3658226"},{"key":"e_1_3_1_40_1","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2014.X.007"},{"key":"e_1_3_1_41_1","article-title":"Multi-Camera LiDAR inertial extension to the newer college dataset","author":"Zhang Lintong","year":"2021","unstructured":"Lintong Zhang, Marco Camurri, and M. Fallon. 2021. Multi-Camera LiDAR inertial extension to the newer college dataset. ArXiv (Dec.2021).","journal-title":"ArXiv"},{"key":"e_1_3_1_42_1","first-page":"586","volume-title":"Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)","author":"Zhang Richard","year":"2018","unstructured":"Richard Zhang, Phillip Isola, Alexei A. Efros, Eli Shechtman, and Oliver Wang. 2018. The Unreasonable effectiveness of deep features as a perceptual metric. In Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition (CVPR). 586\u2013595."},{"key":"e_1_3_1_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72933-1_13"},{"key":"e_1_3_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00096"}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3777909","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T12:27:45Z","timestamp":1766147265000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3777909"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,19]]},"references-count":43,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,4,30]]}},"alternative-id":["10.1145\/3777909"],"URL":"https:\/\/doi.org\/10.1145\/3777909","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"type":"print","value":"0730-0301"},{"type":"electronic","value":"1557-7368"}],"subject":[],"published":{"date-parts":[[2025,12,19]]},"assertion":[{"value":"2025-09-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-11-11","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-12-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}