{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:36:58Z","timestamp":1775230618643,"version":"3.50.1"},"reference-count":83,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T00:00:00Z","timestamp":1750204800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T00:00:00Z","timestamp":1750204800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Shanghai Talent Development Funding","award":["2021016"],"award-info":[{"award-number":["2021016"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1007\/s10489-025-06596-x","type":"journal-article","created":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T06:23:34Z","timestamp":1750227814000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["ClotheDreamer: Text-guided garment generation with 3D gaussians"],"prefix":"10.1007","volume":"55","author":[{"given":"Yufei","family":"Liu","sequence":"first","affiliation":[]},{"given":"Junshu","family":"Tang","sequence":"additional","affiliation":[]},{"given":"Chu","family":"Zheng","sequence":"additional","affiliation":[]},{"given":"Junwei","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Chengjie","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2437-6657","authenticated-orcid":false,"given":"Dongjin","family":"Huang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,6,18]]},"reference":[{"key":"6596_CR1","doi-asserted-by":"crossref","unstructured":"Provot X (1997) Collision and self-collision handling in cloth model dedicated to design garments. In: Computer animation and simulation\u201997: Proceedings of the eurographics workshop in budapest, hungary, September 2\u20133, 1997, Springer, pp 177\u2013189","DOI":"10.1007\/978-3-7091-6874-5_13"},{"key":"6596_CR2","first-page":"767","volume":"2","author":"D Baraff","year":"2023","unstructured":"Baraff D, Witkin A (2023) Large steps in cloth simulation. Seminal graphics papers: Pushing the boundaries 2:767\u2013778","journal-title":"Seminal graphics papers: Pushing the boundaries"},{"key":"6596_CR3","doi-asserted-by":"crossref","unstructured":"Narain R, Samii A, O\u2019brien JF (2012) Adaptive anisotropic remeshing for cloth simulation. ACM Trans Graph (TOG) 31(6):1\u201310","DOI":"10.1145\/2366145.2366171"},{"key":"6596_CR4","doi-asserted-by":"crossref","unstructured":"Li Y, Habermann M, Thomaszewski B, Coros S, Beeler T, Theobalt C (2021) Deep physics-aware inference of cloth deformation for monocular human performance capture. In: 2021 international conference on 3d vision (3DV), IEEE, pp 373\u2013384","DOI":"10.1109\/3DV53792.2021.00047"},{"key":"6596_CR5","unstructured":"Jun H, Nichol A () Shap-e: Generating conditional 3d implicit functions. arXiv preprint arXiv:2305.02463"},{"key":"6596_CR6","unstructured":"Nichol A, Jun H, Dhariwal P, Mishkin P, Chen M (2022) Point-e: A system for generating 3d point clouds from complex prompts. arXiv preprint arXiv:2212.08751"},{"key":"6596_CR7","first-page":"31841","volume":"35","author":"J Gao","year":"2022","unstructured":"Gao J, Shen T, Wang Z, Chen W, Yin K, Li D, Litany O, Gojcic Z, Fidler S (2022) Get3d: A generative model of high quality 3d textured shapes learned from images. Adv Neural Inf Process Syst 35:31841\u201331854","journal-title":"Adv Neural Inf Process Syst"},{"key":"6596_CR8","unstructured":"Qian G, Mai J, Hamdi A, Ren J, Siarohin A, Li B, Lee HY, 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 12th international conference on learning representations (ICLR)"},{"key":"6596_CR9","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":"6596_CR10","unstructured":"Poole B, Jain A, Barron JT, Mildenhall B (2023) Dreamfusion: Text-to-3d using 2d diffusion. In: The 11th international conference on learning representations (ICLR)"},{"key":"6596_CR11","doi-asserted-by":"crossref","unstructured":"Chen R, Chen Y, Jiao N, Jia K (2023) Fantasia3d: Disentangling geometry and appearance for high-quality text-to-3d content creation. In: Proceedings of the IEEE\/CVF international conference on computer vision (ICCV), pp 22246\u201322256","DOI":"10.1109\/ICCV51070.2023.02033"},{"key":"6596_CR12","unstructured":"Tang J, Ren J, Zhou H, Liu Z, Zeng G (2024) Dreamgaussian: Generative gaussian splatting for efficient 3d content creation. In: The 12th international conference on learning representations (ICLR)"},{"key":"6596_CR13","doi-asserted-by":"crossref","unstructured":"Yi T, Fang J, Wang J, Wu G, Xie L, Zhang X, Liu W, Tian Q, Wang X (2024) Gaussiandreamer: Fast generation from text to 3d gaussians by bridging 2d and 3d diffusion models. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR52733.2024.00649"},{"key":"6596_CR14","doi-asserted-by":"crossref","unstructured":"Tang J, Chen Z, Chen X, Wang T, Zeng G, Liu Z (2024) Lgm: Large multi-view gaussian model for high-resolution 3d content creation. In: European conference on computer vision (ECCV), Springer, pp 1\u201318","DOI":"10.1007\/978-3-031-73235-5_1"},{"key":"6596_CR15","doi-asserted-by":"crossref","unstructured":"Lin CH, Gao J, Tang L, Takikawa T, Zeng X, Huang X, Kreis K, Fidler S, Liu MY, Lin TY (2023) Magic3d: High-resolution text-to-3d content creation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 300\u2013309","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"6596_CR16","unstructured":"Tang S, Zhang F, Chen J, Wang P, Furukawa Y (2023) MVDiffusion: Enabling holistic multi-view image generation with correspondence-aware diffusion. In: 37th conference on neural information processing systems"},{"key":"6596_CR17","doi-asserted-by":"crossref","unstructured":"Liu Y, Zhu J, Tang J, Zhang S, Zhang J, Cao W, Wang C, Wu Y, Huang D (2024) Texdreamer: Towards zero-shot high-fidelity 3d human texture generation. In: European conference on computer vision, Springer, pp 184\u2013202","DOI":"10.1007\/978-3-031-72970-6_11"},{"key":"6596_CR18","doi-asserted-by":"crossref","unstructured":"Michel O, Bar-On R, Liu R, Benaim S, Hanocka R (2022) Text2mesh: Text-driven neural stylization for meshes. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR52688.2022.01313"},{"key":"6596_CR19","doi-asserted-by":"crossref","unstructured":"Jiang R, Wang C, Zhang J, Chai M, He M, Chen D, Liao J (2023) Avatarcraft: Transforming text into neural human avatars with parameterized shape and pose control. 2023 IEEE\/CVF international conference on computer vision (ICCV), pp 14325\u201314336","DOI":"10.1109\/ICCV51070.2023.01322"},{"key":"6596_CR20","doi-asserted-by":"crossref","unstructured":"Huang S, Yang Z, Li L, Yang Y, Jia J (2023) Avatarfusion: Zero-shot generation of clothing-decoupled 3d avatars using 2d diffusion. In: Proceedings of the 31st ACM international conference on multimedia, pp 5734\u20135745","DOI":"10.1145\/3581783.3612022"},{"issue":"4","key":"6596_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3528223.3530094","volume":"41","author":"F Hong","year":"2022","unstructured":"Hong F, Zhang M, Pan L, Cai Z, Yang L, Liu Z (2022) Avatarclip: Zero-shot text-driven generation and animation of 3d avatars. ACM Trans Graph (TOG) 41(4):1\u201319","journal-title":"ACM Trans Graph (TOG)"},{"issue":"1","key":"6596_CR22","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1145\/3503250","volume":"65","author":"B Mildenhall","year":"2021","unstructured":"Mildenhall B, Srinivasan PP, Tancik M, Barron JT, Ramamoorthi R, Ng R (2021) Nerf: Representing scenes as neural radiance fields for view synthesis. Commun ACM 65(1):99\u2013106","journal-title":"Commun ACM"},{"issue":"4","key":"6596_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3592433","volume":"42","author":"B Kerbl","year":"2023","unstructured":"Kerbl B, Kopanas G, Leimk\u00fchler T, Drettakis G (2023) 3d gaussian splatting for real-time radiance field rendering. ACM Trans Graph 42(4):1\u201314","journal-title":"ACM Trans Graph"},{"key":"6596_CR24","first-page":"6087","volume":"34","author":"T Shen","year":"2021","unstructured":"Shen T, Gao J, Yin K, Liu MY, Fidler S (2021) Deep marching tetrahedra: a hybrid representation for high-resolution 3d shape synthesis. Adv Neural Inf Process Syst 34:6087\u20136101","journal-title":"Adv Neural Inf Process Syst"},{"key":"6596_CR25","doi-asserted-by":"crossref","unstructured":"Wang J, Liu Y, Dou Z, Yu Z, Liang Y, Lin C, Xie R, Song L, Li X, Wang W (2024) Disentangled clothed avatar generation from text descriptions. In: European conference on computer vision, springer, pp 381\u2013401","DOI":"10.1007\/978-3-031-72943-0_22"},{"key":"6596_CR26","doi-asserted-by":"crossref","unstructured":"Liao T, Yi H, Xiu Y, Tang J, Huang Y, Thies J, Black MJ (2024) TADA! text to animatable digital avatars. In: InternationalcConference on 3D vision (3DV)","DOI":"10.1109\/3DV62453.2024.00150"},{"key":"6596_CR27","unstructured":"Wang Z, Lu C, Wang Y, Bao F, Li C, Su H, Zhu J (2024) Prolificdreamer: High-fidelity and diverse text-to-3d generation with variational score distillation. Adv Neural Inf Process Syst 36"},{"key":"6596_CR28","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: 2024 IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR52733.2024.00635"},{"key":"6596_CR29","doi-asserted-by":"crossref","unstructured":"Pavlakos G, Choutas V, Ghorbani N, Bolkart T, Osman AA, Tzionas D, Black MJ (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":"6596_CR30","first-page":"851","volume":"2","author":"M Loper","year":"2023","unstructured":"Loper M, Mahmood N, Romero J, Pons-Moll G, Black MJ (2023) Smpl: A skinned multi-person linear model. Seminal graphics papers: Pushing the boundaries 2:851\u2013866","journal-title":"Seminal graphics papers: Pushing the boundaries"},{"key":"6596_CR31","doi-asserted-by":"crossref","unstructured":"Casado-Elvira A, Trinidad MC, Casas D (2022) Pergamo: Personalized 3d garments from monocular video. In: Computer graphics forum, vol 41. Wiley Online Library, pp 293\u2013304","DOI":"10.1111\/cgf.14644"},{"issue":"6","key":"6596_CR32","first-page":"1","volume":"37","author":"TY Wang","year":"2018","unstructured":"Wang TY, Ceylan D, Popovic J, Mitra NJ (2018) Learning a shared shape space for multimodal garment design. ACM Trans Graph (TOG) 37(6):1\u201313","journal-title":"ACM Trans Graph (TOG)"},{"key":"6596_CR33","doi-asserted-by":"crossref","unstructured":"Tiwari G, Bhatnagar BL, Tung T, Pons-Moll G (2020) Sizer: A dataset and model for parsing 3d clothing and learning size sensitive 3d clothing. In: Computer vision\u2013ECCV 2020: 16th European conference, glasgow, UK, August 23\u201328, 2020, Proceedings, Part III 16, Springer, pp 1\u201318","DOI":"10.1007\/978-3-030-58580-8_1"},{"key":"6596_CR34","doi-asserted-by":"crossref","unstructured":"Gundogdu E, Constantin V, Seifoddini A, Dang M, Salzmann M, Fua P (2019) Garnet: A two-stream network for fast and accurate 3d cloth draping. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 8739\u20138748","DOI":"10.1109\/ICCV.2019.00883"},{"key":"6596_CR35","doi-asserted-by":"crossref","unstructured":"Grigorev A, Black MJ, Hilliges O (2023) Hood: Hierarchical graphs for generalized modelling of clothing dynamics. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 16965\u201316974","DOI":"10.1109\/CVPR52729.2023.01627"},{"key":"6596_CR36","doi-asserted-by":"crossref","unstructured":"Xue Y, Bhatnagar BL, Marin R, Sarafianos N, Xu Y, Pons-Moll G, Tung T (2023) Nsf: Neural surface fields for human modeling from monocular depth. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 15049\u201315060","DOI":"10.1109\/ICCV51070.2023.01382"},{"key":"6596_CR37","unstructured":"Li R, Guillard B, Fua P (2023) ISP: Multi-layered garment draping with implicit sewing patterns. In: 37th conference on neural information processing systems"},{"issue":"6","key":"6596_CR38","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3478513.3480479","volume":"40","author":"H Bertiche","year":"2021","unstructured":"Bertiche H, Madadi M, Escalera S (2021) Pbns: Physically based neural simulator for unsupervised garment pose space deformation. ACM Trans Graph (TOG) 40(6):1\u201314","journal-title":"ACM Trans Graph (TOG)"},{"key":"6596_CR39","doi-asserted-by":"crossref","unstructured":"Ma Q, Yang J, Ranjan A, Pujades S, Pons-Moll G, Tang S, Black MJ (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":"6596_CR40","doi-asserted-by":"crossref","unstructured":"Pan X, Mai J, Jiang X, Tang D, Li J, Shao T, Zhou K, Jin X, Manocha D (2022) Predicting loose-fitting garment deformations using bone-driven motion networks. In: ACM SIGGRAPH 2022 conference proceedings, pp 1\u201310","DOI":"10.1145\/3528233.3530709"},{"key":"6596_CR41","doi-asserted-by":"crossref","unstructured":"Santesteban I, Otaduy MA, Casas D (2022) Snug: Self-supervised neural dynamic garments. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 8140\u20138150","DOI":"10.1109\/CVPR52688.2022.00797"},{"key":"6596_CR42","doi-asserted-by":"crossref","unstructured":"Bertiche H, Madadi M, Tylson E, Escalera S (2021) Deepsd: Automatic deep skinning and pose space deformation for 3d garment animation. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 5471\u20135480","DOI":"10.1109\/ICCV48922.2021.00542"},{"issue":"1","key":"6596_CR43","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1109\/TPAMI.2020.3010886","volume":"44","author":"E Gundogdu","year":"2020","unstructured":"Gundogdu E, Constantin V, Parashar S, Seifoddini A, Dang M, Salzmann M, Fua P (2020) Garnet++: Improving fast and accurate static 3d cloth draping by curvature loss. IEEE Trans Patt Anal Mach Intell 44(1):181\u2013195","journal-title":"IEEE Trans Patt Anal Mach Intell"},{"key":"6596_CR44","doi-asserted-by":"crossref","unstructured":"Lahner Z, Cremers D, Tung T (2018) Deepwrinkles: Accurate and realistic clothing modeling. In: Proceedings of the european conference on computer vision (ECCV), pp 667\u2013684","DOI":"10.1007\/978-3-030-01225-0_41"},{"issue":"6","key":"6596_CR45","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3550454.3555469","volume":"41","author":"M Zhang","year":"2022","unstructured":"Zhang M, Ceylan D, Mitra NJ (2022) Motion guided deep dynamic 3d garments. ACM Trans Graph (TOG) 41(6):1\u201312","journal-title":"ACM Trans Graph (TOG)"},{"key":"6596_CR46","first-page":"15147","volume":"35","author":"X Chen","year":"2022","unstructured":"Chen X, Wang G, Zhu D, Liang X, Torr P, Lin L (2022) Structure-preserving 3d garment modeling with neural sewing machines. Adv Neural Inf Process Syst 35:15147\u201315159","journal-title":"Adv Neural Inf Process Syst"},{"issue":"2","key":"6596_CR47","doi-asserted-by":"publisher","first-page":"1581","DOI":"10.1109\/TPAMI.2022.3168569","volume":"45","author":"Z Su","year":"2022","unstructured":"Su Z, Yu T, Wang Y, Liu Y (2022) Deepcloth: Neural garment representation for shape and style editing. IEEE Trans Patt Anal Mach Intell 45(2):1581\u20131593","journal-title":"IEEE Trans Patt Anal Mach Intell"},{"key":"6596_CR48","doi-asserted-by":"crossref","unstructured":"Li R, Guillard B, Remelli E, Fua P (2022) Dig: Draping implicit garment over the human body. In: Proceedings of the Asian conference on computer vision, pp 2780\u20132795","DOI":"10.1007\/978-3-031-26319-4_21"},{"key":"6596_CR49","doi-asserted-by":"crossref","unstructured":"Corona E, Pumarola A, Alenya G, Pons-Moll G, Moreno-Noguer F (2021) Smplicit: Topology-aware generative model for clothed people. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 11875\u201311885","DOI":"10.1109\/CVPR46437.2021.01170"},{"key":"6596_CR50","doi-asserted-by":"crossref","unstructured":"De\u00a0Luigi L, Li R, Guillard B, Salzmann M, Fua P (2023) Drapenet: Garment generation and self-supervised draping. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 1451\u20131460","DOI":"10.1109\/CVPR52729.2023.00146"},{"key":"6596_CR51","doi-asserted-by":"crossref","unstructured":"Li Y, Chen Hy, Larionov E, Sarafianos N, Matusik W, Stuyck T (2024) DiffAvatar: Simulation-ready garment optimization with differentiable simulation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR52733.2024.00418"},{"key":"6596_CR52","doi-asserted-by":"crossref","unstructured":"Tang J, Wang T, Zhang B, Zhang T, Yi R, Ma L, Chen D (2023) Make-it-3d: High-fidelity 3d creation from a single image with diffusion prior. In: Proceedings of the IEEE\/CVF international conference on computer vision (ICCV), pp 22819\u201322829","DOI":"10.1109\/ICCV51070.2023.02086"},{"key":"6596_CR53","doi-asserted-by":"crossref","unstructured":"Tang J, Zeng Y, Fan K, Wang X, Dai B, Chen K, Ma L (2024) Make-it-vivid: Dressing your animatable biped cartoon characters from text. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 6243\u20136253","DOI":"10.1109\/CVPR52733.2024.00597"},{"key":"6596_CR54","doi-asserted-by":"crossref","unstructured":"Karnewar A, Vedaldi A, Novotny D, Mitra NJ (2023) Holodiffusion: Training a 3d diffusion model using 2d images. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 18423\u201318433","DOI":"10.1109\/CVPR52729.2023.01767"},{"issue":"4","key":"6596_CR55","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3658147","volume":"43","author":"K He","year":"2024","unstructured":"He K, Yao K, Zhang Q, Yu J, Liu L, Xu L (2024) Dresscode: Autoregressively sewing and generating garments from text guidance. ACM Trans Graph (TOG) 43(4):1\u201313","journal-title":"ACM Trans Graph (TOG)"},{"key":"6596_CR56","first-page":"27730","volume":"35","author":"L Ouyang","year":"2022","unstructured":"Ouyang L, Wu J, Jiang X, Almeida D, Wainwright C, Mishkin P, Zhang C, Agarwal S, Slama K, Ray A et al (2022) Training language models to follow instructions with human feedback. Adv Neural Inf Process Syst 35:27730\u201327744","journal-title":"Adv Neural Inf Process Syst"},{"key":"6596_CR57","doi-asserted-by":"crossref","unstructured":"Li B, Li X, Jiang Y, Xie T, Gao F, Wang H, Yang Y, Jiang C (2025) Garmentdreamer: 3dgs guided garment synthesis with diverse geometry and texture details. In: International conference on 3d vision (3DV)","DOI":"10.1109\/3DV66043.2025.00134"},{"key":"6596_CR58","doi-asserted-by":"crossref","unstructured":"Chen Z, Wang F, Wang Y, Liu H (2024) Text-to-3d using gaussian splatting. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 21401\u201321412","DOI":"10.1109\/CVPR52733.2024.02022"},{"key":"6596_CR59","doi-asserted-by":"crossref","unstructured":"Liang Y, Yang X, Lin J, Li H, Xu X, Chen Y (2024) Luciddreamer: Towards high-fidelity text-to-3d generation via interval score matching. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 6517\u20136526","DOI":"10.1109\/CVPR52733.2024.00623"},{"key":"6596_CR60","unstructured":"Zeng Y, Lu Y, Ji X, Yao Y, Zhu H, Cao X (2023) Avatarbooth: High-quality and customizable 3d human avatar generation. arXiv preprint arXiv:2306.09864"},{"key":"6596_CR61","doi-asserted-by":"crossref","unstructured":"Cao Y, Cao YP, Han K, Shan Y, Wong KYK (2024) Dreamavatar: Text-and-shape guided 3d human avatar generation via diffusion models. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 958\u2013968","DOI":"10.1109\/CVPR52733.2024.00097"},{"key":"6596_CR62","unstructured":"Kolotouros N, Alldieck T, Zanfir A, Bazavan E, Fieraru M, Sminchisescu C (2024) Dreamhuman: Animatable 3d avatars from text. Adv Neural Inf Process Syst 36"},{"key":"6596_CR63","doi-asserted-by":"crossref","unstructured":"Huang X, Shao R, Zhang Q, Zhang H, Feng Y, Liu Y, Wang Q (2024) Humannorm: Learning normal diffusion model for high-quality and realistic 3d human generation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 4568\u20134577","DOI":"10.1109\/CVPR52733.2024.00437"},{"key":"6596_CR64","unstructured":"Wang P, Liu L, Liu Y, Theobalt C, Komura T, Wang W (2021) Neus: Learning neural implicit surfaces by volume rendering for multi-view reconstruction. Adv Neural Inf Process Syst"},{"key":"6596_CR65","unstructured":"Radford A, Kim JW, Hallacy C, Ramesh A, Goh G, Agarwal S, Sastry G, Askell A, Mishkin P, Clark J et al (2021) Learning transferable visual models from natural language supervision. In: International conference on machine learning, PMLR, pp 8748\u20138763"},{"key":"6596_CR66","unstructured":"Huang Y, Wang J, Zeng A, Cao H, Qi X, Shi Y, Zha ZJ, Zhang L (2024) Dreamwaltz: Make a scene with complex 3d animatable avatars. Adv Neural Inf Process Syst 36"},{"key":"6596_CR67","doi-asserted-by":"crossref","unstructured":"Yuan Y, Li X, Huang Y, De\u00a0Mello S, Nagano K, Kautz J, Iqbal U (2024) Gavatar: Animatable 3d gaussian avatars with implicit mesh learning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 896\u2013905","DOI":"10.1109\/CVPR52733.2024.00091"},{"key":"6596_CR68","unstructured":"Hong F, Chen Z, LAN Y, Pan L, Liu Z (2023) EVA3d: Compositional 3d human generation from 2d image collections. In: The 11th international conference on learning representations"},{"key":"6596_CR69","doi-asserted-by":"crossref","unstructured":"Xu Y, Yifan W, Bergman AW, Chai M, Zhou B, Wetzstein G (2024) Efficient 3d articulated human generation with layered surface volumes. In: 2024 international conference on 3D vision (3DV), IEEE, pp 268\u2013279","DOI":"10.1109\/3DV62453.2024.00047"},{"key":"6596_CR70","doi-asserted-by":"crossref","unstructured":"Dong J, Fang Q, Huang Z, Xu X, Wang J, Peng S, Dai B (2024) Tela: Text to layer-wise 3d clothed human generation. In: European conference on computer vision, Springer, pp 19\u201336","DOI":"10.1007\/978-3-031-72698-9_2"},{"key":"6596_CR71","doi-asserted-by":"crossref","unstructured":"Snavely N, Seitz SM, Szeliski R (2006) Photo tourism: exploring photo collections in 3d. In: ACM siggraph 2006 papers, pp 835\u2013846","DOI":"10.1145\/1141911.1141964"},{"key":"6596_CR72","doi-asserted-by":"crossref","unstructured":"Zwicker M, Pfister H, Van\u00a0Baar J, Gross M (2001) Ewa volume splatting. In: Proceedings Visualization, 2001. VIS\u201901., IEEE, pp 29\u2013538","DOI":"10.1109\/VISUAL.2001.964490"},{"key":"6596_CR73","unstructured":"Marvelous Designer (2023) 2024.: Official Site. https:\/\/www.marvelousdesigner.com\/"},{"key":"6596_CR74","doi-asserted-by":"crossref","unstructured":"Rusinkiewicz S, Levoy M (2001) Efficient variants of the icp algorithm. In: Proceedings 3rd international conference on 3-D digital imaging and modeling, IEEE, pp 145\u2013152","DOI":"10.1109\/IM.2001.924423"},{"key":"6596_CR75","doi-asserted-by":"crossref","unstructured":"Muja M, Lowe DG (2014) Scalable nearest neighbor algorithms for high dimensional data. IEEE Trans Patt Anal Mach Intell 36","DOI":"10.1109\/TPAMI.2014.2321376"},{"key":"6596_CR76","doi-asserted-by":"crossref","unstructured":"Fridovich-Keil S, Yu A, Tancik M, Chen Q, Recht B, Kanazawa A (2022) Plenoxels: Radiance fields without neural networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 5501\u20135510","DOI":"10.1109\/CVPR52688.2022.00542"},{"key":"6596_CR77","unstructured":"Guo YC, Liu YT, Shao R, Laforte C, Voleti V, Luo G, Chen CH, Zou ZX, Wang C, Cao YP, Zhang SH (2023) threestudio: A unified framework for 3D content generation. https:\/\/github.com\/threestudio-project\/threestudio"},{"key":"6596_CR78","unstructured":"Kim S, Shin J, Cho Y, Jang J, Longpre S, Lee H, Yun S, Shin S, Kim S, Thorne J, Seo M (2024) Prometheus: Inducing fine-grained evaluation capability in language models. In: The 12th international conference on learning representations"},{"key":"6596_CR79","unstructured":"Heusel M, Ramsauer H, Unterthiner T, Nessler B, Hochreiter S (2017) Gans trained by a two time-scale update rule converge to a local nash equilibrium. Adv Neural Inf Process Syst 30"},{"key":"6596_CR80","doi-asserted-by":"crossref","unstructured":"Chen Z, Wu J, Wang W, Su W, Chen G, Xing S, Zhong M, Zhang Q, Zhu X, Lu L et al (2024) Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 24185\u201324198","DOI":"10.1109\/CVPR52733.2024.02283"},{"key":"6596_CR81","doi-asserted-by":"crossref","unstructured":"Lin S, Liu B, Li J, Yang X (2024) Common diffusion noise schedules and sample steps are flawed. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision, pp 5404\u20135411","DOI":"10.1109\/WACV57701.2024.00532"},{"key":"6596_CR82","unstructured":"Katzir O, Patashnik O, Cohen-Or D, Lischinski D (2024) Noise-free score distillation. In: The 12th international conference on learning representations"},{"key":"6596_CR83","doi-asserted-by":"crossref","unstructured":"Jiang Y, Tu J, Liu Y, Gao X, Long X, Wang W, Ma Y (2024) Gaussianshader: 3d gaussian splatting with shading functions for reflective surfaces. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 5322\u20135332","DOI":"10.1109\/CVPR52733.2024.00509"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-025-06596-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-025-06596-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-025-06596-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T13:58:36Z","timestamp":1758290316000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-025-06596-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,18]]},"references-count":83,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2025,7]]}},"alternative-id":["6596"],"URL":"https:\/\/doi.org\/10.1007\/s10489-025-06596-x","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,18]]},"assertion":[{"value":"25 April 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 June 2025","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All authors certify that they have no affiliations with or involvement in any organization or entity with any financial interest or non-financial interest in the subject matter or materials discussed in this manuscript.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"Informed consent was obtained from all individual participants included in the study. The participant has consented to the submission of the case report to the journal.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}}],"article-number":"767"}}