{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:17:32Z","timestamp":1781533052212,"version":"3.54.5"},"reference-count":31,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["42371457"],"award-info":[{"award-number":["42371457"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["42301468"],"award-info":[{"award-number":["42301468"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61902330"],"award-info":[{"award-number":["61902330"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"award":["42371457"],"award-info":[{"award-number":["42371457"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"publisher"}]},{"award":["42301468"],"award-info":[{"award-number":["42301468"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"publisher"}]},{"award":["61902330"],"award-info":[{"award-number":["61902330"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"publisher"}]},{"name":"Natural Science Foundation of Fujian Province, China","award":["2023J01803"],"award-info":[{"award-number":["2023J01803"]}]},{"name":"Natural Science Foundation of Fujian Province, China","award":["2022J01337"],"award-info":[{"award-number":["2022J01337"]}]},{"name":"Natural Science Foundation of Fujian Province, China","award":["2022J01819"],"award-info":[{"award-number":["2022J01819"]}]},{"name":"Natural Science Foundation of Fujian Province, China","award":["2023J01801"],"award-info":[{"award-number":["2023J01801"]}]},{"name":"Natural Science Foundation of Fujian Province, China","award":["2023J01799"],"award-info":[{"award-number":["2023J01799"]}]},{"name":"Natural Science Foundation of Fujian Province, China","award":["2022J05157"],"award-info":[{"award-number":["2022J05157"]}]},{"name":"Natural Science Foundation of Fujian Province, China","award":["2022J011394"],"award-info":[{"award-number":["2022J011394"]}]},{"name":"Natural Science Foundation of Xiamen, China","award":["3502Z202371019"],"award-info":[{"award-number":["3502Z202371019"]}]},{"name":"Natural Science Foundation of Xiamen, China","award":["3502Z202373036"],"award-info":[{"award-number":["3502Z202373036"]}]},{"name":"Natural Science Foundation of Xiamen, China","award":["3502Z20227048"],"award-info":[{"award-number":["3502Z20227048"]}]},{"name":"Natural Science Foundation of Xiamen, China","award":["3502Z20227049"],"award-info":[{"award-number":["3502Z20227049"]}]},{"name":"Open Competition for Innovative Projects of Xiamen, China","award":["3502Z20231038"],"award-info":[{"award-number":["3502Z20231038"]}]},{"name":"Open Competition for Innovative Projects of Xiamen, China","award":["3502Z20251012"],"award-info":[{"award-number":["3502Z20251012"]}]},{"name":"Startup Fund of Jimei University","award":["ZQ2022031"],"award-info":[{"award-number":["ZQ2022031"]}]},{"award":["ZQ2022031"],"award-info":[{"award-number":["ZQ2022031"]}],"id":[{"id":"https:\/\/ror.org\/03hknyb50","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>Three-dimensional Gaussian Splatting (3DGS) methods have achieved real-time rendering and high-precision modeling in 3D human avatar modeling. However, most existing methods perform Gaussian sphere cloning, splitting, and pruning without explicit geometric constraints in density control, resulting in inadequate detail reconstruction. To address this, we propose a Gaussian Adaptive Density Control method with SDF constraints (GADC-SDF). Specifically, we introduce the Signed Distance Field (SDF) as explicit geometric constraints for adaptive density control in 3DGS optimization. First, SDF voxel grids are constructed from the SMPL-X mesh. Then, SDF values are applied to prune spheres outside the human body, while additional Gaussian spheres are cloned around the human surface. Furthermore, SDF gradients are utilized to split more Gaussian spheres in detail-rich regions. Experiments conducted on X-Humans, UPB, and ZJU_MoCap datasets demonstrate that our method matches the performance of state-of-the-art baselines across most quantitative metrics while providing a modest improvement in perceptual quality.<\/jats:p>","DOI":"10.3390\/a19040273","type":"journal-article","created":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T14:59:01Z","timestamp":1775055541000},"page":"273","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Gaussian Adaptive Density Control with SDF Constraints (GADC-SDF) for 3D Human Avatar Modeling"],"prefix":"10.3390","volume":"19","author":[{"given":"Yebing","family":"Sun","sequence":"first","affiliation":[{"name":"School of Computer Engineering, Jimei University, Xiamen 361000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5978-7619","authenticated-orcid":false,"given":"Min","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computer Engineering, Jimei University, Xiamen 361000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gangbo","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computer Engineering, Jimei University, Xiamen 361000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenbo","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Computer Engineering, Jimei University, Xiamen 361000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shi","family":"He","sequence":"additional","affiliation":[{"name":"School of Computer Engineering, Jimei University, Xiamen 361000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Engineering, Jimei University, Xiamen 361000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinhe","family":"Su","sequence":"additional","affiliation":[{"name":"School of Computer Engineering, Jimei University, Xiamen 361000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,4,1]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Zhao, F., Yang, W., Zhang, J., Lin, P., Zhang, Y., Yu, J., and Xu, L. (2022). Humannerf: Efficiently generated human radiance field from sparse inputs. 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR52688.2022.00759"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Peng, S., Zhang, Y., Xu, Y., Wang, Q., Shuai, Q., Bao, H., and Zhou, X. (2021). Neural body: Implicit neural representations with structured latent codes for novel view synthesis of dynamic humans. 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR46437.2021.00894"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Jiang, W., Yi, K.M., Samei, G., Tuzel, O., and Ranjan, A. (2022). Neuman: Neural human radiance field from a single video. Computer Vision\u2014ECCV 2022, Springer.","DOI":"10.1007\/978-3-031-19824-3_24"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1145\/3592433","article-title":"3D Gaussian splatting for real-time radiance field rendering","volume":"42","author":"Kerbl","year":"2023","journal-title":"ACM Trans. Graph."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Chen, P., Wei, X., Wuwu, Q., Wang, X., Xiao, X., and Lu, M. (2025). MixedGaussianAvatar: Realistically and Geometrically Accurate Head Avatar via Mixed 2D-3D Gaussians. MM \u201925: Proceedings of the 33rd ACM International Conference on Multimedia, Association for Computing Machinery.","DOI":"10.1145\/3746027.3754756"},{"key":"ref_6","unstructured":"Dutta, A., Zheng, M., Gao, Z., Planche, B., Choudhuri, A., Chen, T., Roy-Chowdhury, A.K., and Wu, Z. (2025, January 19\u201325). Chrome: Clothed human reconstruction with occlusion-resilience and multiview-consistency from a single image. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Honolulu, HI, USA."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"113470","DOI":"10.1016\/j.knosys.2025.113470","article-title":"Uv gaussians: Joint learning of mesh deformation and gaussian textures for human avatar modeling","volume":"320","author":"Jiang","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Guo, C., Li, J., Kant, Y., Sheikh, Y., Saito, S., and Cao, C. (2025, January 11\u201315). Vid2avatar-pro: Authentic avatar from videos in the wild via universal prior. Proceedings of the Computer Vision and Pattern Recognition Conference, Nashville, TN, USA.","DOI":"10.1109\/CVPR52734.2025.00522"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Liu, X., and Wu, C. (2025). VGA: Reconstructing Vivid 3D Gaussian Avatars from Monocular Videos. Computational Visual Media, Springer.","DOI":"10.1007\/978-981-96-5812-1_10"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Choi, S., Choi, M., Jang, M., Kim, J., Cai, J., Cheng, W.H., and Lee, S. (2025). Relightable and Dynamic Gaussian Avatar Reconstruction from Monocular Video. MM \u201925: Proceedings of the 33rd ACM International Conference on Multimedia, Association for Computing Machinery.","DOI":"10.1145\/3746027.3754851"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"248","DOI":"10.1145\/2816795.2818013","article-title":"SMPL: A skinned multi-person linear model","volume":"34","author":"Loper","year":"2015","journal-title":"ACM Trans. Graph."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., Choutas, V., Ghorbani, N., Bolkart, T., Osman, A.A., Tzionas, D., and Black, M.J. (2019). Expressive body capture: 3d hands, face, and body from a single image. 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR.2019.01123"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Hu, S., Hu, T., and Liu, Z. (2024). Gauhuman: Articulated gaussian splatting from monocular human videos. 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR52733.2024.01930"},{"key":"ref_14","first-page":"5646","article-title":"Expressive gaussian human avatars from monocular rgb video","volume":"37","author":"Hu","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Park, J.J., Florence, P., Straub, J., Newcombe, R., and Lovegrove, S. (2019). Deepsdf: Learning continuous signed distance functions for shape representation. 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR.2019.00025"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Xiang, H., Li, X., Cheng, K., Lai, X., Zhang, W., Liao, Z., Zeng, L., and Liu, X. (2025). Gaussianroom: Improving 3d gaussian splatting with sdf guidance and monocular cues for indoor scene reconstruction. 2025 IEEE International Conference on Robotics and Automation (ICRA), IEEE.","DOI":"10.1109\/ICRA55743.2025.11127828"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Svitov, D., Morerio, P., Agapito, L., and Del Bue, A. (2024). Haha: Highly articulated gaussian human avatars with textured mesh prior. Computer Vision\u2014ACCV 2024, Springer.","DOI":"10.1007\/978-981-96-0969-7_7"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Weng, C.Y., Curless, B., Srinivasan, P.P., Barron, J.T., and Kemelmacher-Shlizerman, I. (2022). Humannerf: Free-viewpoint rendering of moving people from monocular video. 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR52688.2022.01573"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1145\/3503250","article-title":"Nerf: Representing scenes as neural radiance fields for view synthesis","volume":"65","author":"Mildenhall","year":"2021","journal-title":"Commun. ACM"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Joo, H., Simon, T., and Sheikh, Y. (2018). Total capture: A 3d deformation model for tracking faces, hands, and bodies. 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2018.00868"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Shen, K., Guo, C., Kaufmann, M., Zarate, J.J., Valentin, J., Song, J., and Hilliges, O. (2023). X-avatar: Expressive human avatars. 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR52729.2023.01622"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Moon, G., Shiratori, T., and Saito, S. (2024). Expressive whole-body 3d gaussian avatar. Computer Vision\u2014ECCV 2024, Springer.","DOI":"10.1007\/978-3-031-72940-9_2"},{"key":"ref_23","unstructured":"Fardo, F.A., Conforto, V.H., De Oliveira, F.C., and Rodrigues, P.S. (2016). A formal evaluation of PSNR as quality measurement parameter for image segmentation algorithms. arXiv."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1109\/TIP.2003.819861","article-title":"Image quality assessment: From error visibility to structural similarity","volume":"13","author":"Wang","year":"2004","journal-title":"IEEE Trans. Image Process."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., and Wang, O. (2018). The unreasonable effectiveness of deep features as a perceptual metric. 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Qian, Z., Wang, S., Mihajlovic, M., Geiger, A., and Tang, S. (2024). 3dgs-avatar: Animatable avatars via deformable 3d gaussian splatting. 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR52733.2024.00480"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Lei, J., Wang, Y., Pavlakos, G., Liu, L., and Daniilidis, K. (2024). Gart: Gaussian articulated template models. 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR52733.2024.01879"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Hu, L., Zhang, H., Zhang, Y., Zhou, B., Liu, B., Zhang, S., and Nie, L. (2024). Gaussianavatar: Towards realistic human avatar modeling from a single video via animatable 3d gaussians. 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR52733.2024.00067"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Remelli, E., Bagautdinov, T., Saito, S., Wu, C., Simon, T., Wei, S.E., Guo, K., Cao, Z., Prada, F., and Saragih, J. (2022). Drivable volumetric avatars using texel-aligned features. SIGGRAPH \u201922: ACM SIGGRAPH 2022 Conference Proceedings, Association for Computing Machinery.","DOI":"10.1145\/3528233.3530740"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Geng, C., Peng, S., Xu, Z., Bao, H., and Zhou, X. (2023). Learning neural volumetric representations of dynamic humans in minutes. 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR52729.2023.00846"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Jiang, T., Chen, X., Song, J., and Hilliges, O. (2023). Instantavatar: Learning avatars from monocular video in 60 seconds. 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR52729.2023.01623"}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/19\/4\/273\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:19:04Z","timestamp":1775189944000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/19\/4\/273"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,1]]},"references-count":31,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2026,4]]}},"alternative-id":["a19040273"],"URL":"https:\/\/doi.org\/10.3390\/a19040273","relation":{},"ISSN":["1999-4893"],"issn-type":[{"value":"1999-4893","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,1]]}}}