{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T21:16:51Z","timestamp":1764969411751,"version":"3.46.0"},"reference-count":54,"publisher":"Association for Computing Machinery (ACM)","issue":"6","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62372336"],"award-info":[{"award-number":["62372336"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Graph."],"published-print":{"date-parts":[[2025,12]]},"abstract":"<jats:p>Existing 3D Gaussian (3DGS) based methods tend to produce blurriness and artifacts on delicate textures (small objects and high-frequency textures) in aerial large-scale scenes. The reason is that the delicate textures usually occupy a relatively small number of pixels, and the accumulated gradients from loss function are difficult to promote the splitting of 3DGS. To minimize the rendering error, the model will use a small number of large Gaussians to cover these details, resulting in blurriness and artifacts. To solve the above problem, we propose a novel hierarchical Gaussian: JumpingGS. JumpingGS assigns different levels to Gaussians to establish a hierarchical representation. Low-level Gaussians are responsible for the coarse appearance, while high-level Gaussians are responsible for the details. First, we design a splitting strategy that allows low-level Gaussians to skip intermediate levels and directly split the appropriate high-level Gaussians for delicate textures. This level-jump splitting ensures that the weak gradients of delicate textures can always activate a higher level instead of being ignored by the intermediate levels. Second, JumpingGS reduces the gradient and opacity thresholds for density control according to the representation levels, which improves the sensitivity of high-level Gaussians to delicate textures. Third, we design a novel training strategy to detect training views in hard-to-observe regions, and train the model multiple times on these views to alleviate underfitting. Experiments on aerial large-scale scenes demonstrate that JumpingGS outperforms existing 3DGS-based methods, accurately and efficiently recovering delicate textures in large scenes.<\/jats:p>","DOI":"10.1145\/3763347","type":"journal-article","created":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T17:15:39Z","timestamp":1764868539000},"page":"1-15","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["JumpingGS: Level-jump 3D Gaussian Representation for Delicate Textures in Aerial Large-scale Scene Rendering"],"prefix":"10.1145","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4990-3430","authenticated-orcid":false,"given":"Jiongming","family":"Qin","sequence":"first","affiliation":[{"name":"School of Computer Science, Wuhan University, Wuhan, Hubei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0071-165X","authenticated-orcid":false,"given":"Kaixuan","family":"Zhou","sequence":"additional","affiliation":[{"name":"Riemann Lab, Huawei Technologies, Wuhan, Hubei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6912-849X","authenticated-orcid":false,"given":"Yu","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University, Wuhan, Hubei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6083-8452","authenticated-orcid":false,"given":"Huizhi","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University, Wuhan, Hubei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7320-5144","authenticated-orcid":false,"given":"Fei","family":"Luo","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University, Wuhan, Hubei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4526-6297","authenticated-orcid":false,"given":"Chunxia","family":"Xiao","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University, Wuhan, Hubei, China"}]}],"member":"320","published-online":{"date-parts":[[2025,12,4]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00580"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00539"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01804"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00794"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00183"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00021"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_20"},{"key":"e_1_2_1_8_1","volume-title":"Pgsr: Planar-based gaussian splatting for efficient and high-fidelity surface reconstruction","author":"Chen Danpeng","year":"2024","unstructured":"Danpeng Chen, Hai Li, Weicai Ye, Yifan Wang, Weijian Xie, Shangjin Zhai, Nan Wang, Haomin Liu, Hujun Bao, and Guofeng Zhang. 2024. Pgsr: Planar-based gaussian splatting for efficient and high-fidelity surface reconstruction. IEEE Transactions on Visualization and Computer Graphics (2024)."},{"key":"e_1_2_1_9_1","unstructured":"Hanlin Chen Chen Li and Gim Hee Lee. 2023. NeuSG: Neural Implicit Surface Reconstruction with 3D Gaussian Splatting Guidance. arXiv:2312.00846 [cs.CV] https:\/\/arxiv.org\/abs\/2312.00846"},{"key":"e_1_2_1_10_1","volume-title":"Forty-first International Conference on Machine Learning.","author":"Cheng Kai","year":"2024","unstructured":"Kai Cheng, Xiaoxiao Long, Kaizhi Yang, Yao Yao, Wei Yin, Yuexin Ma, Wenping Wang, and Xuejin Chen. 2024. Gaussianpro: 3d gaussian splatting with progressive propagation. In Forty-first International Conference on Machine Learning."},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01201"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00512"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00013"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3658160"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01192"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00297"},{"key":"e_1_2_1_18_1","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision. 18547\u201318557","author":"Li Zongcheng","year":"2023","unstructured":"Zongcheng Li, Xiaoxiao Long, Yusen Wang, Tuo Cao, Wenping Wang, Fei Luo, and Chunxia Xiao. 2023b. NeTO: neural reconstruction of transparent objects with self-occlusion aware refraction-tracing. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 18547\u201318557."},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00817"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00569"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00494"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_6"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72640-8_15"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01952"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3687952"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00713"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"e_1_2_1_28_1","volume-title":"Instant neural graphics primitives with a multiresolution hash encoding. ACM transactions on graphics (TOG) 41, 4","author":"M\u00fcller Thomas","year":"2022","unstructured":"Thomas M\u00fcller, Alex Evans, Christoph Schied, and Alexander Keller. 2022. Instant neural graphics primitives with a multiresolution hash encoding. ACM transactions on graphics (TOG) 41, 4 (2022), 1\u201315."},{"key":"e_1_2_1_29_1","volume-title":"European Conference on Computer Vision. Springer, 19\u201337","author":"Paliwal Avinash","year":"2024","unstructured":"Avinash Paliwal, Wei Ye, Jinhui Xiong, Dmytro Kotovenko, Rakesh Ranjan, Vikas Chandra, and Nima Khademi Kalantari. 2024. Coherentgs: Sparse novel view synthesis with coherent 3d gaussians. In European Conference on Computer Vision. Springer, 19\u201337."},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681436"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01407"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01259"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3568201"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00538"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00807"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01258"},{"volume-title":"NeuS: Learning Neural Implicit Surfaces by","author":"Wang Peng","key":"e_1_2_1_37_1","unstructured":"Peng Wang, Lingjie Liu, Yuan Liu, Christian Theobalt, Taku Komura, and Wenping Wang. 2021. NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction. In Advances in Neural Information Processing Systems, M. Ranzato, A. Beygelzimer, Y. Dauphin, P.S. Liang, and J. Wortman Vaughan (Eds.), Vol. 34. Curran Associates, Inc., 27171\u201327183."},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00404"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3550454.3555514"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3618390"},{"key":"e_1_2_1_41_1","volume-title":"Voxurf: Voxel-based Efficient and Accurate Neural Surface Reconstruction. Int. Conf. Learn. Represent.","author":"Wu Tong","year":"2023","unstructured":"Tong Wu, Jiaqi Wang, Xingang Pan, Xudong Xu, Christian Theobalt, Ziwei Liu, and Dahua Lin. 2023. Voxurf: Voxel-based Efficient and Accurate Neural Surface Reconstruction. Int. Conf. Learn. Represent. (2023)."},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_7"},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00802"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-2095-8_4"},{"key":"e_1_2_1_45_1","volume-title":"Street Gaussians for Modeling Dynamic Urban Scenes. In Eur. Conf. Comput. Vis.","author":"Yan Yunzhi","year":"2024","unstructured":"Yunzhi Yan, Haotong Lin, Chenxu Zhou, Weijie Wang, Haiyang Sun, Kun Zhan, Xianpeng Lang, Xiaowei Zhou, and Sida Peng. 2024. Street Gaussians for Modeling Dynamic Urban Scenes. In Eur. Conf. Comput. Vis."},{"key":"e_1_2_1_46_1","first-page":"61192","article-title":"Spec-gaussian: Anisotropic view-dependent appearance for 3d gaussian splatting","volume":"37","author":"Yang Ziyi","year":"2024","unstructured":"Ziyi Yang, Xinyu Gao, Yang-Tian Sun, Yihua Huang, Xiaoyang Lyu, Wen Zhou, Shaohui Jiao, Xiaojuan Qi, and Xiaogang Jin. 2024. Spec-gaussian: Anisotropic view-dependent appearance for 3d gaussian splatting. Advances in Neural Information Processing Systems 37 (2024), 61192\u201361216.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591536"},{"key":"e_1_2_1_48_1","first-page":"129507","article-title":"Gsdf: 3dgs meets sdf for improved neural rendering and reconstruction","volume":"37","author":"Yu Mulin","year":"2024","unstructured":"Mulin Yu, Tao Lu, Linning Xu, Lihan Jiang, Yuanbo Xiangli, and Bo Dai. 2024b. Gsdf: 3dgs meets sdf for improved neural rendering and reconstruction. Advances in Neural Information Processing Systems 37 (2024), 129507\u2013129530.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_49_1","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 19447\u201319456","author":"Yu Zehao","year":"2024","unstructured":"Zehao Yu, Anpei Chen, Binbin Huang, Torsten Sattler, and Andreas Geiger. 2024a. Mipsplatting: Alias-free 3d gaussian splatting. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 19447\u201319456."},{"key":"e_1_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3687937"},{"key":"e_1_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2022.3170695"},{"key":"e_1_2_1_52_1","volume-title":"European Conference on Computer Vision. Springer, 14\u201336","author":"Zhao Hexu","year":"2024","unstructured":"Hexu Zhao, Haoyang Weng, Daohan Lu, Ang Li, Jinyang Li, Aurojit Panda, and Saining Xie. 2024. On scaling up 3d gaussian splatting training. In European Conference on Computer Vision. Springer, 14\u201336."},{"key":"e_1_2_1_53_1","volume-title":"The Eleventh International Conference on Learning Representations.","author":"Zhenxing MI","year":"2022","unstructured":"MI Zhenxing and Dan Xu. 2022. Switch-nerf: Learning scene decomposition with mixture of experts for large-scale neural radiance fields. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_2_1_54_1","doi-asserted-by":"crossref","unstructured":"Xiaoyu Zhou Zhiwei Lin Xiaojun Shan Yongtao Wang Deqing Sun and Ming-Hsuan Yang. 2024. Drivinggaussian: Composite gaussian splatting for surrounding dynamic autonomous driving scenes. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 21634\u201321643. Matthias Zwicker Hanspeter Pfister Jeroen Van Baar and Markus Gross. 2001. Ewa volume splatting. In Proceedings Visualization 2001. VIS'01. IEEE 29\u2013538.","DOI":"10.1109\/CVPR52733.2024.02044"}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3763347","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T21:13:28Z","timestamp":1764969208000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3763347"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":54,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["10.1145\/3763347"],"URL":"https:\/\/doi.org\/10.1145\/3763347","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"type":"print","value":"0730-0301"},{"type":"electronic","value":"1557-7368"}],"subject":[],"published":{"date-parts":[[2025,12]]},"assertion":[{"value":"2025-05-22","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-08-09","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-12-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}