{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T14:46:44Z","timestamp":1782485204623,"version":"3.54.5"},"reference-count":83,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376285"],"award-info":[{"award-number":["62376285"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61673396"],"award-info":[{"award-number":["61673396"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Engineering Applications of Artificial Intelligence"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.engappai.2026.115335","type":"journal-article","created":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T12:37:44Z","timestamp":1781527064000},"page":"115335","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"P2","title":["Optimization-based fast single-image three-dimensional clothed human reconstruction via Gaussian Splatting"],"prefix":"10.1016","volume":"181","author":[{"given":"Xinyuan","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7323-5896","authenticated-orcid":false,"given":"Mingwen","family":"Shao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiang","family":"Lv","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.engappai.2026.115335_b1","doi-asserted-by":"crossref","unstructured":"Abdal, R., Yifan, W., Shi, Z., Xu, Y., Po, R., Kuang, Z., Chen, Q., Yeung, D.-Y., Wetzstein, G., 2024. Gaussian shell maps for efficient 3d human generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 9441\u20139451.","DOI":"10.1109\/CVPR52733.2024.00902"},{"key":"10.1016\/j.engappai.2026.115335_b2","doi-asserted-by":"crossref","unstructured":"AlBahar, B., Saito, S., Tseng, H.-Y., Kim, C., Kopf, J., Huang, J.-B., 2023. Single-image 3d human digitization with shape-guided diffusion. In: SIGGRAPH Asia 2023 Conference Papers. pp. 1\u201311.","DOI":"10.1145\/3610548.3618153"},{"key":"10.1016\/j.engappai.2026.115335_b3","doi-asserted-by":"crossref","unstructured":"Alldieck, T., Zanfir, M., Sminchisescu, C., 2022. Photorealistic monocular 3d reconstruction of humans wearing clothing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 1506\u20131515.","DOI":"10.1109\/CVPR52688.2022.00156"},{"key":"10.1016\/j.engappai.2026.115335_b4","series-title":"Proceedings of COMPSTAT\u20192010: 19th International Conference on Computational StatisticsParis France, August 22-27, 2010 Keynote, Invited and Contributed Papers","first-page":"177","article-title":"Large-scale machine learning with stochastic gradient descent","author":"Bottou","year":"2010"},{"key":"10.1016\/j.engappai.2026.115335_b5","series-title":"Ultraman: Single image 3D human reconstruction with ultra speed and detail","author":"Chen","year":"2024"},{"key":"10.1016\/j.engappai.2026.115335_b6","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"2416","article-title":"Single-stage diffusion nerf: A unified approach to 3d generation and reconstruction","author":"Chen","year":"2023"},{"key":"10.1016\/j.engappai.2026.115335_b7","unstructured":"Chen, J., Li, C., Zhang, J., Zhu, L., Huang, B., Chen, H., Lee, G.H., 2025. Generalizable Human Gaussians from Single-View Image. In: International Conference on Learning Representations. ICLR."},{"key":"10.1016\/j.engappai.2026.115335_b8","doi-asserted-by":"crossref","DOI":"10.3389\/frai.2025.1709229","article-title":"Human reconstruction using 3D Gaussian splatting: a brief survey","volume":"8","author":"Chen","year":"2025","journal-title":"Front. Artif. Intell."},{"key":"10.1016\/j.engappai.2026.115335_b9","series-title":"Eurographics Italian Chapter Conference","first-page":"129","article-title":"Meshlab: an open-source mesh processing tool.","volume":"2008","author":"Cignoni","year":"2008"},{"key":"10.1016\/j.engappai.2026.115335_b10","doi-asserted-by":"crossref","unstructured":"Corona, E., Zanfir, M., Alldieck, T., Bazavan, E.G., Zanfir, A., Sminchisescu, C., 2023. Structured 3d features for reconstructing controllable avatars. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 16954\u201316964.","DOI":"10.1109\/CVPR52729.2023.01626"},{"key":"10.1016\/j.engappai.2026.115335_b11","doi-asserted-by":"crossref","unstructured":"Dai, P., Xu, J., Xie, W., Liu, X., Wang, H., Xu, W., 2024. High-quality surface reconstruction using gaussian surfels. In: ACM SIGGRAPH 2024 Conference Papers. pp. 1\u201311.","DOI":"10.1145\/3641519.3657441"},{"key":"10.1016\/j.engappai.2026.115335_b12","doi-asserted-by":"crossref","unstructured":"Gao, X., Li, X., Zhang, C., Zhang, Q., Cao, Y., Shan, Y., Quan, L., 2024. Contex-human: Free-view rendering of human from a single image with texture-consistent synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 10084\u201310094.","DOI":"10.1109\/CVPR52733.2024.00961"},{"key":"10.1016\/j.engappai.2026.115335_b13","doi-asserted-by":"crossref","unstructured":"Guo, C., Jiang, T., Chen, X., Song, J., Hilliges, O., 2023. Vid2avatar: 3d avatar reconstruction from videos in the wild via self-supervised scene decomposition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 12858\u201312868.","DOI":"10.1109\/CVPR52729.2023.01236"},{"key":"10.1016\/j.engappai.2026.115335_b14","doi-asserted-by":"crossref","unstructured":"Han, S.-H., Park, M.-G., Yoon, J.H., Kang, J.-M., Park, Y.-J., Jeon, H.-G., 2023. High-fidelity 3d human digitization from single 2k resolution images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 12869\u201312879.","DOI":"10.1109\/CVPR52729.2023.01237"},{"key":"10.1016\/j.engappai.2026.115335_b15","doi-asserted-by":"crossref","unstructured":"Ho, I., Song, J., Hilliges, O., et al., 2024. Sith: Single-view textured human reconstruction with image-conditioned diffusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 538\u2013549.","DOI":"10.1109\/CVPR52733.2024.00058"},{"key":"10.1016\/j.engappai.2026.115335_b16","doi-asserted-by":"crossref","unstructured":"Hong, J.G., Noh, S.Y., Lee, H.K., Cheong, W.S., Chang, J.Y., 2024. 3D Clothed Human Reconstruction from Sparse Multi-view Images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 677\u2013687.","DOI":"10.1109\/CVPRW63382.2024.00072"},{"key":"10.1016\/j.engappai.2026.115335_b17","doi-asserted-by":"crossref","unstructured":"Hu, S., Hong, F., Pan, L., Mei, H., Yang, L., Liu, Z., 2023. Sherf: Generalizable human nerf from a single image. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 9352\u20139364.","DOI":"10.1109\/ICCV51070.2023.00858"},{"key":"10.1016\/j.engappai.2026.115335_b18","doi-asserted-by":"crossref","unstructured":"Hu, S., Hu, T., Liu, Z., 2024. Gauhuman: Articulated gaussian splatting from monocular human videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 20418\u201320431.","DOI":"10.1109\/CVPR52733.2024.01930"},{"key":"10.1016\/j.engappai.2026.115335_b19","doi-asserted-by":"crossref","unstructured":"Hu, L., Zhang, H., Zhang, Y., Zhou, B., Liu, B., Zhang, S., Nie, L., 2024. Gaussianavatar: Towards realistic human avatar modeling from a single video via animatable 3d gaussians. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 634\u2013644.","DOI":"10.1109\/CVPR52733.2024.00067"},{"key":"10.1016\/j.engappai.2026.115335_b20","series-title":"2024 International Conference on 3D Vision (3DV)","first-page":"1531","article-title":"Tech: Text-guided reconstruction of lifelike clothed humans","author":"Huang","year":"2024"},{"key":"10.1016\/j.engappai.2026.115335_b21","doi-asserted-by":"crossref","unstructured":"Jiang, T., Chen, X., Song, J., Hilliges, O., 2023. Instantavatar: Learning avatars from monocular video in 60 seconds. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 16922\u201316932.","DOI":"10.1109\/CVPR52729.2023.01623"},{"issue":"4","key":"10.1016\/j.engappai.2026.115335_b22","doi-asserted-by":"crossref","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":"10.1016\/j.engappai.2026.115335_b23","doi-asserted-by":"crossref","unstructured":"Kim, B., Kwon, P., Lee, K., Lee, M., Han, S., Kim, D., Joo, H., 2023. Chupa: Carving 3d clothed humans from skinned shape priors using 2d diffusion probabilistic models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 15965\u201315976.","DOI":"10.1109\/ICCV51070.2023.01463"},{"key":"10.1016\/j.engappai.2026.115335_b24","unstructured":"Kingma, D.P., Ba, J., 2015. Adam: A Method for Stochastic Optimization. In: International Conference on Learning Representations. ICLR."},{"key":"10.1016\/j.engappai.2026.115335_b25","first-page":"24741","article-title":"Neural human performer: Learning generalizable radiance fields for human performance rendering","volume":"34","author":"Kwon","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"6","key":"10.1016\/j.engappai.2026.115335_b26","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3414685.3417861","article-title":"Modular primitives for high-performance differentiable rendering","volume":"39","author":"Laine","year":"2020","journal-title":"ACM Trans. Graph. (ToG)"},{"key":"10.1016\/j.engappai.2026.115335_b27","series-title":"International Conference on Machine Learning","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"10.1016\/j.engappai.2026.115335_b28","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2025.112431","article-title":"Plug-and-play dynamic optimization for three-dimensional Gaussian generation","volume":"162","author":"Li","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"issue":"6","key":"10.1016\/j.engappai.2026.115335_b29","first-page":"1","article-title":"Neural actor: Neural free-view synthesis of human actors with pose control","volume":"40","author":"Liu","year":"2021","journal-title":"ACM Trans. Graph."},{"key":"10.1016\/j.engappai.2026.115335_b30","doi-asserted-by":"crossref","unstructured":"Liu, L., Li, Y., Gao, Y., Gao, C., Liu, Y., Chen, J., 2024. VS: Reconstructing Clothed 3D Human from Single Image via Vertex Shift. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 10498\u201310507.","DOI":"10.1109\/CVPR52733.2024.00999"},{"key":"10.1016\/j.engappai.2026.115335_b31","doi-asserted-by":"crossref","unstructured":"Liu, M., Shi, R., Chen, L., Zhang, Z., Xu, C., Wei, X., Chen, H., Zeng, C., Gu, J., Su, H., 2024. One-2-3-45++: Fast single image to 3d objects with consistent multi-view generation and 3d diffusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 10072\u201310083.","DOI":"10.1109\/CVPR52733.2024.00960"},{"key":"10.1016\/j.engappai.2026.115335_b32","doi-asserted-by":"crossref","unstructured":"Liu, R., Wu, R., Van Hoorick, B., Tokmakov, P., Zakharov, S., Vondrick, C., 2023. Zero-1-to-3: Zero-shot one image to 3d object. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 9298\u20139309.","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"10.1016\/j.engappai.2026.115335_b33","doi-asserted-by":"crossref","unstructured":"Liu, X., Zhan, X., Tang, J., Shan, Y., Zeng, G., Lin, D., Liu, X., Liu, Z., 2024. Humangaussian: Text-driven 3d human generation with gaussian splatting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 6646\u20136657.","DOI":"10.1109\/CVPR52733.2024.00635"},{"key":"10.1016\/j.engappai.2026.115335_b34","doi-asserted-by":"crossref","unstructured":"Long, X., Guo, Y.-C., Lin, C., Liu, Y., Dou, Z., Liu, L., Ma, Y., Zhang, S.-H., Habermann, M., Theobalt, C., et al., 2024. Wonder3d: Single image to 3d using cross-domain diffusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 9970\u20139980.","DOI":"10.1109\/CVPR52733.2024.00951"},{"key":"10.1016\/j.engappai.2026.115335_b35","series-title":"Seminal Graphics Papers: Pushing the Boundaries, Volume 2","first-page":"851","article-title":"SMPL: A skinned multi-person linear model","author":"Loper","year":"2023"},{"key":"10.1016\/j.engappai.2026.115335_b36","series-title":"Seminal Graphics: Pioneering Efforts that Shaped the Field","first-page":"347","article-title":"Marching cubes: A high resolution 3D surface construction algorithm","author":"Lorensen","year":"1998"},{"key":"10.1016\/j.engappai.2026.115335_b37","doi-asserted-by":"crossref","unstructured":"Ma, Q., Yang, J., Ranjan, A., Pujades, S., Pons-Moll, G., Tang, S., Black, M.J., 2020. Learning to dress 3d people in generative clothing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 6469\u20136478.","DOI":"10.1109\/CVPR42600.2020.00650"},{"key":"10.1016\/j.engappai.2026.115335_b38","unstructured":"Meng, C., He, Y., Song, Y., Song, J., Wu, J., Zhu, J.-Y., Ermon, S., 2022. SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations. In: International Conference on Learning Representations."},{"key":"10.1016\/j.engappai.2026.115335_b39","doi-asserted-by":"crossref","unstructured":"Moreau, A., Song, J., Dhamo, H., Shaw, R., Zhou, Y., P\u00e9rez-Pellitero, E., 2024. Human gaussian splatting: Real-time rendering of animatable avatars. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 788\u2013798.","DOI":"10.1109\/CVPR52733.2024.00081"},{"issue":"5","key":"10.1016\/j.engappai.2026.115335_b40","doi-asserted-by":"crossref","DOI":"10.1002\/cav.2101","article-title":"Continuous remeshing for inverse rendering","volume":"33","author":"Palfinger","year":"2022","journal-title":"Comput. Animat. Virtual Worlds"},{"key":"10.1016\/j.engappai.2026.115335_b41","doi-asserted-by":"crossref","first-page":"74383","DOI":"10.52202\/079017-2367","article-title":"Humansplat: Generalizable single-image human gaussian splatting with structure priors","volume":"37","author":"Pan","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.engappai.2026.115335_b42","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., Choutas, V., Ghorbani, N., Bolkart, T., Osman, A.A., Tzionas, D., Black, M.J., 2019. Expressive body capture: 3d hands, face, and body from a single image. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 10975\u201310985.","DOI":"10.1109\/CVPR.2019.01123"},{"key":"10.1016\/j.engappai.2026.115335_b43","doi-asserted-by":"crossref","unstructured":"Peng, S., Dong, J., Wang, Q., Zhang, S., Shuai, Q., Zhou, X., Bao, H., 2021. Animatable neural radiance fields for modeling dynamic human bodies. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 14314\u201314323.","DOI":"10.1109\/ICCV48922.2021.01405"},{"key":"10.1016\/j.engappai.2026.115335_b44","series-title":"Dreamfusion: Text-to-3d using 2d diffusion","author":"Poole","year":"2022"},{"key":"10.1016\/j.engappai.2026.115335_b45","unstructured":"Qian, G., Mai, J., Hamdi, A., Ren, J., Siarohin, A., Li, B., Lee, H.-Y., Skorokhodov, I., Wonka, P., Tulyakov, S., Ghanem, B., 2024. Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors. In: The Twelfth International Conference on Learning Representations. ICLR."},{"key":"10.1016\/j.engappai.2026.115335_b46","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2020.107404","article-title":"U2-net: Going deeper with nested U-structure for salient object detection","volume":"106","author":"Qin","year":"2020","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.engappai.2026.115335_b47","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.engappai.2026.115335_b48","series-title":"Dreamgaussian4d: Generative 4d gaussian splatting","author":"Ren","year":"2023"},{"key":"10.1016\/j.engappai.2026.115335_b49","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B., 2022. High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 10684\u201310695.","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"10.1016\/j.engappai.2026.115335_b50","doi-asserted-by":"crossref","unstructured":"Saito, S., Huang, Z., Natsume, R., Morishima, S., Kanazawa, A., Li, H., 2019. Pifu: Pixel-aligned implicit function for high-resolution clothed human digitization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 2304\u20132314.","DOI":"10.1109\/ICCV.2019.00239"},{"key":"10.1016\/j.engappai.2026.115335_b51","doi-asserted-by":"crossref","unstructured":"Saito, S., Simon, T., Saragih, J., Joo, H., 2020. Pifuhd: Multi-level pixel-aligned implicit function for high-resolution 3d human digitization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 84\u201393.","DOI":"10.1109\/CVPR42600.2020.00016"},{"key":"10.1016\/j.engappai.2026.115335_b52","doi-asserted-by":"crossref","unstructured":"Saito, S., Yang, J., Ma, Q., Black, M.J., 2021. SCANimate: Weakly supervised learning of skinned clothed avatar networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 2886\u20132897.","DOI":"10.1109\/CVPR46437.2021.00291"},{"key":"10.1016\/j.engappai.2026.115335_b53","doi-asserted-by":"crossref","unstructured":"Sengupta, A., Alldieck, T., Kolotouros, N., Corona, E., Zanfir, A., Sminchisescu, C., 2024. DiffHuman: Probabilistic Photorealistic 3D Reconstruction of Humans. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 1439\u20131449.","DOI":"10.1109\/CVPR52733.2024.00143"},{"key":"10.1016\/j.engappai.2026.115335_b54","doi-asserted-by":"crossref","unstructured":"Shao, Z., Wang, Z., Li, Z., Wang, D., Lin, X., Zhang, Y., Fan, M., Wang, Z., 2024. Splattingavatar: Realistic real-time human avatars with mesh-embedded gaussian splatting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 1606\u20131616.","DOI":"10.1109\/CVPR52733.2024.00159"},{"key":"10.1016\/j.engappai.2026.115335_b55","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2025.3569596","article-title":"Gamba: Marry gaussian splatting with mamba for single-view 3d reconstruction","author":"Shen","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.engappai.2026.115335_b56","series-title":"Zero123++: a single image to consistent multi-view diffusion base model","author":"Shi","year":"2023"},{"key":"10.1016\/j.engappai.2026.115335_b57","doi-asserted-by":"crossref","unstructured":"Song, D.-Y., Lee, H., Seo, J., Cho, D., 2023. Difu: Depth-guided implicit function for clothed human reconstruction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 8738\u20138747.","DOI":"10.1109\/CVPR52729.2023.00844"},{"key":"10.1016\/j.engappai.2026.115335_b58","doi-asserted-by":"crossref","unstructured":"Szymanowicz, S., Rupprecht, C., Vedaldi, A., 2024. Splatter image: Ultra-fast single-view 3d reconstruction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 10208\u201310217.","DOI":"10.1109\/CVPR52733.2024.00972"},{"key":"10.1016\/j.engappai.2026.115335_b59","unstructured":"Tang, J., Ren, J., Zhou, H., Liu, Z., Zeng, G., 2024. Dreamgaussian: Generative gaussian splatting for efficient 3d content creation. In: The Twelfth International Conference on Learning Representations. ICLR."},{"issue":"6","key":"10.1016\/j.engappai.2026.115335_b60","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3687927","article-title":"GaussianHeads: End-to-end learning of drivable Gaussian head avatars from coarse-to-fine representations","volume":"43","author":"Teotia","year":"2024","journal-title":"ACM Trans. Graph."},{"issue":"12","key":"10.1016\/j.engappai.2026.115335_b61","doi-asserted-by":"crossref","first-page":"15406","DOI":"10.1109\/TPAMI.2023.3298850","article-title":"Recovering 3d human mesh from monocular images: A survey","volume":"45","author":"Tian","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.engappai.2026.115335_b62","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.engappai.2026.115335_b63","series-title":"European Conference on Computer Vision","first-page":"439","article-title":"Sv3d: Novel multi-view synthesis and 3d generation from a single image using latent video diffusion","author":"Voleti","year":"2024"},{"issue":"4","key":"10.1016\/j.engappai.2026.115335_b64","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":"10.1016\/j.engappai.2026.115335_b65","article-title":"CloCap-GS: clothed human performance capture with 3D Gaussian splatting","author":"Wang","year":"2025","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.engappai.2026.115335_b66","doi-asserted-by":"crossref","unstructured":"Wen, H., Huang, Z., Wang, Y., Chen, X., Sheng, L., 2025. Ouroboros3d: Image-to-3d generation via 3d-aware recursive diffusion. In: Proceedings of the Computer Vision and Pattern Recognition Conference. pp. 21631\u201321641.","DOI":"10.1109\/CVPR52734.2025.02015"},{"key":"10.1016\/j.engappai.2026.115335_b67","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, B., Go, H., Kim, J.-Y., Kim, C., 2024. Harmonyview: Harmonizing consistency and diversity in one-image-to-3d. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 10574\u201310584.","DOI":"10.1109\/CVPR52733.2024.01006"},{"key":"10.1016\/j.engappai.2026.115335_b68","series-title":"Unique3D: High-quality and efficient 3D mesh generation from a single image","author":"Wu","year":"2024"},{"key":"10.1016\/j.engappai.2026.115335_b69","doi-asserted-by":"crossref","unstructured":"Xiang, J., Lv, Z., Xu, S., Deng, Y., Wang, R., Zhang, B., Chen, D., Tong, X., Yang, J., 2025. Structured 3d latents for scalable and versatile 3d generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 21469\u201321480.","DOI":"10.1109\/CVPR52734.2025.02000"},{"key":"10.1016\/j.engappai.2026.115335_b70","doi-asserted-by":"crossref","unstructured":"Xiu, Y., Yang, J., Cao, X., Tzionas, D., Black, M.J., 2023. Econ: Explicit clothed humans optimized via normal integration. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 512\u2013523.","DOI":"10.1109\/CVPR52729.2023.00057"},{"key":"10.1016\/j.engappai.2026.115335_b71","series-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"13286","article-title":"Icon: Implicit clothed humans obtained from normals","author":"Xiu","year":"2022"},{"key":"10.1016\/j.engappai.2026.115335_b72","series-title":"Instantmesh: Efficient 3d mesh generation from a single image with sparse-view large reconstruction models","author":"Xu","year":"2024"},{"key":"10.1016\/j.engappai.2026.115335_b73","doi-asserted-by":"crossref","unstructured":"Yang, Y., Liu, D., Zhang, S., Deng, Z., Huang, Z., Tan, M., 2024. HiLo: Detailed and Robust 3D Clothed Human Reconstruction with High-and Low-Frequency Information of Parametric Models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 10671\u201310681.","DOI":"10.1109\/CVPR52733.2024.01015"},{"key":"10.1016\/j.engappai.2026.115335_b74","doi-asserted-by":"crossref","unstructured":"Yu, T., Zheng, Z., Guo, K., Liu, P., Dai, Q., Liu, Y., 2021. Function4d: Real-time human volumetric capture from very sparse consumer rgbd sensors. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 5746\u20135756.","DOI":"10.1109\/CVPR46437.2021.00569"},{"key":"10.1016\/j.engappai.2026.115335_b75","series-title":"European Conference on Computer Vision","first-page":"1","article-title":"Gs-lrm: Large reconstruction model for 3d gaussian splatting","author":"Zhang","year":"2024"},{"key":"10.1016\/j.engappai.2026.115335_b76","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O., 2018. The unreasonable effectiveness of deep features as a perceptual metric. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 586\u2013595.","DOI":"10.1109\/CVPR.2018.00068"},{"key":"10.1016\/j.engappai.2026.115335_b77","doi-asserted-by":"crossref","unstructured":"Zhang, J., Li, X., Zhang, Q., Cao, Y., Shan, Y., Liao, J., 2024. Humanref: Single image to 3d human generation via reference-guided diffusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 1844\u20131854.","DOI":"10.1109\/CVPR52733.2024.00181"},{"key":"10.1016\/j.engappai.2026.115335_b78","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M., 2023. Adding conditional control to text-to-image diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 3836\u20133847.","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"10.1016\/j.engappai.2026.115335_b79","article-title":"Global-correlated 3d-decoupling transformer for clothed avatar reconstruction","volume":"36","author":"Zhang","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.engappai.2026.115335_b80","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Yang, Z., Yang, Y., 2024. Sifu: Side-view conditioned implicit function for real-world usable clothed human reconstruction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 9936\u20139947.","DOI":"10.1109\/CVPR52733.2024.00948"},{"issue":"1","key":"10.1016\/j.engappai.2026.115335_b81","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1016\/j.visinf.2022.03.002","article-title":"Metaverse: Perspectives from graphics, interactions and visualization","volume":"6","author":"Zhao","year":"2022","journal-title":"Vis. Inform."},{"issue":"6","key":"10.1016\/j.engappai.2026.115335_b82","doi-asserted-by":"crossref","first-page":"3170","DOI":"10.1109\/TPAMI.2021.3050505","article-title":"Pamir: Parametric model-conditioned implicit representation for image-based human reconstruction","volume":"44","author":"Zheng","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.engappai.2026.115335_b83","doi-asserted-by":"crossref","unstructured":"Zhuang, Y., Lv, J., Wen, H., Shuai, Q., Zeng, A., Zhu, H., Chen, S., Yang, Y., Cao, X., Liu, W., 2025. Idol: Instant photorealistic 3d human creation from a single image. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 26308\u201326319.","DOI":"10.1109\/CVPR52734.2025.02450"}],"container-title":["Engineering Applications of Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197626016192?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197626016192?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T13:55:17Z","timestamp":1782482117000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0952197626016192"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":83,"alternative-id":["S0952197626016192"],"URL":"https:\/\/doi.org\/10.1016\/j.engappai.2026.115335","relation":{},"ISSN":["0952-1976"],"issn-type":[{"value":"0952-1976","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Optimization-based fast single-image three-dimensional clothed human reconstruction via Gaussian Splatting","name":"articletitle","label":"Article Title"},{"value":"Engineering Applications of Artificial Intelligence","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.engappai.2026.115335","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"115335"}}