{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T12:09:43Z","timestamp":1779365383773,"version":"3.53.0"},"reference-count":62,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1007\/s00371-026-04494-y","type":"journal-article","created":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T09:45:29Z","timestamp":1778060729000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A comprehensive soft spatial control of human motion generation via dual stage diffusion"],"prefix":"10.1007","volume":"42","author":[{"given":"Yixuan","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,6]]},"reference":[{"key":"4494_CR1","doi-asserted-by":"crossref","unstructured":"Guo, C., Mu, Y., Javed, M.G., Wang, S., Cheng, L.: MoMask: generative masked modeling of 3D human motions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1900\u20131910 (2024)","DOI":"10.1109\/CVPR52733.2024.00186"},{"key":"4494_CR2","doi-asserted-by":"crossref","unstructured":"Guo, C., Zou, S., Zuo, X., Wang, S., Ji, W., Li, X., Cheng, L.: Generating diverse and natural 3d human motions from text. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5152\u20135161 (2022)","DOI":"10.1109\/CVPR52688.2022.00509"},{"issue":"6","key":"4494_CR3","doi-asserted-by":"publisher","first-page":"4115","DOI":"10.1109\/TPAMI.2024.3355414","volume":"46","author":"M Zhang","year":"2024","unstructured":"Zhang, M., Cai, Z., Pan, L., Hong, F., Guo, X., Yang, L., Liu, Z.: MotionDiffuse: text-driven human motion generation with diffusion model. IEEE Trans. Pattern Anal. Mach. Intell. 46(6), 4115\u20134128 (2024)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"4494_CR4","doi-asserted-by":"crossref","unstructured":"Zhang, M., Guo, X., Pan, L., Cai, Z., Hong, F., Li, H., Yang, L., Liu, Z.: ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 364\u2013373 (2023)","DOI":"10.1109\/ICCV51070.2023.00040"},{"key":"4494_CR5","doi-asserted-by":"crossref","unstructured":"Zhang, J., Zhang, Y., Cun, X., Zhang, Y., Zhao, H., Lu, H., Shen, X., Shan, Y.: Generating human motion from textual descriptions with discrete representations. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14730\u201314740 (2023)","DOI":"10.1109\/CVPR52729.2023.01415"},{"key":"4494_CR6","unstructured":"Tevet, G., Raab, S., Gordon, B., Shafir, Y., Cohen-Or, D., Bermano, A.H.: Human motion diffusion model. In: 2023, The 11th International Conference on Learning Representations (ICLR 2023) (2023)"},{"key":"4494_CR7","unstructured":"Shafir, Y., Tevet, G., Kapon, R., Bermano, A.H.: Human motion diffusion as a generative prior. In: The 12th International Conference on Learning Representations (ICLR 2024) (2024)"},{"key":"4494_CR8","doi-asserted-by":"crossref","unstructured":"Karunratanakul, K., Preechakul, K., Suwajanakorn, S., Tang, S.: Guided motion diffusion for controllable human motion synthesis. In: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), Paris, France, pp. 2151\u20132162. IEEE (2023)","DOI":"10.1109\/ICCV51070.2023.00205"},{"key":"4494_CR9","unstructured":"Xie, Y., Jampani, V., Zhong, L., Sun, D., Jiang, H.: Omnicontrol: control any joint at any time for human motion generation. In: Kim, B., Yue, Y., Chaudhuri, S., Fragkiadaki, K., Khan, M., Sun, Y. (eds.) The 12th International Conference on Learning Representations (ICLR 2024), vol. 2024, pp. 28176\u201328194 (2024)"},{"key":"4494_CR10","doi-asserted-by":"crossref","unstructured":"Cohan, S., Tevet, G., Reda, D., Peng, X.B., van\u00a0de Panne, M.: Flexible motion in-betweening with diffusion models. In: ACM SIGGRAPH 2024 Conference Papers, vol. 69, pp. 1\u20139 (2024)","DOI":"10.1145\/3641519.3657414"},{"key":"4494_CR11","unstructured":"Zhao, Y., Zhang, Y., Yang, X.: IKMo: image-keyframed motion generation with trajectory-pose conditioned motion diffusion model. arXiv preprint arXiv:2505.21146 (2025)"},{"key":"4494_CR12","doi-asserted-by":"crossref","unstructured":"Jiang, N., He, Z., Wang, Z., Li, H., Chen, Y., Huang, S., Zhu, Y.: Autonomous character-scene interaction synthesis from text instruction. In: SIGGRAPH Asia 2024 Conference Papers, Tokyo Japan, pp. 1\u201311. ACM (2024)","DOI":"10.1145\/3680528.3687595"},{"key":"4494_CR13","doi-asserted-by":"crossref","unstructured":"Lim, D., Jeong, C., Kim, Y.M.: MAMMOS: mapping multiple human motion with scene understanding and natural interactions. In: 2023 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW), Paris, France, pp. 4280\u20134289. IEEE (2023)","DOI":"10.1109\/ICCVW60793.2023.00462"},{"key":"4494_CR14","doi-asserted-by":"crossref","unstructured":"Liu, X., Hou, H., Yang, Y., Li, Y.-L., Lu, C.: Revisit human-scene interaction via space occupancy. In: European Conference on Computer Vision (ECCV) (2024)","DOI":"10.1007\/978-3-031-72973-7_1"},{"key":"4494_CR15","unstructured":"Xiao, Z., Wang, T., Wang, J., Cao, J., Zhang, W., Dai, B., Lin, D., Pang, J.: Unified human-scene interaction via prompted chain-of-contacts. In International Conference on Learning Representations (ICLR). Poster: Halle B #11 (2024)"},{"key":"4494_CR16","doi-asserted-by":"publisher","first-page":"246","DOI":"10.1007\/978-3-031-73235-5_14","volume-title":"Computer Vision\u2013ECCV 2024","author":"H Yi","year":"2025","unstructured":"Yi, H., Thies, J., Black, M.J., Peng, X.B., Rempe, D.: Generating human interaction motions in scenes with text control. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) Computer Vision\u2013ECCV 2024, vol. 15062, pp. 246\u2013263. Springer Nature, Cham (2025)"},{"key":"4494_CR17","doi-asserted-by":"crossref","unstructured":"Zhao, K., Zhang, Y., Wang, S., Beeler, T., Tang, S.: Synthesizing diverse human motions in 3D indoor scenes. In: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), Paris, France, pp. 14692\u201314703. IEEE (2023)","DOI":"10.1109\/ICCV51070.2023.01354"},{"issue":"8","key":"4494_CR18","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1007\/s10514-023-10131-7","volume":"47","author":"K Lin","year":"2023","unstructured":"Lin, K., Agia, C., Migimatsu, T., Pavone, M., Bohg, J.: Text2Motion: from natural language instructions to feasible plans. Auton. Robot. 47(8), 1345\u20131365 (2023)","journal-title":"Auton. Robot."},{"key":"4494_CR19","unstructured":"Jiang, Y., Cun, X., Zhang, Y., Zheng, Y., Tang, F., Pun, C.M.: Emocast: emotional talking portrait via emotive text description. arXiv preprint arXiv:2508.20615 (2025)"},{"key":"4494_CR20","doi-asserted-by":"crossref","unstructured":"Li, L., Wang, S., Zhimeng Zhang, Yu., Ding, Y.Z., Xin, Y., Fan, C.: Write-a-speaker: text-based emotional and rhythmic talking-head generation. Proc. AAAI Confer. Artif. Intell. 35(3), 1911\u20131920 (2021)","DOI":"10.1609\/aaai.v35i3.16286"},{"key":"4494_CR21","doi-asserted-by":"crossref","unstructured":"Lin, Y., Fung, H., Xu, J., Ren, Z., Lau, A.S., Yin, G., Li, X.: Mvportrait: text-guided motion and emotion control for multi-view vivid portrait animation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 26242\u201326252 (2025)","DOI":"10.1109\/CVPR52734.2025.02444"},{"key":"4494_CR22","doi-asserted-by":"crossref","unstructured":"Wang, Y., Guo, J., Bai, J., Runyi, Yu., Tianyu He, X., Sun, T.X., Bian, J.: Instructavatar: text-guided emotion and motion control for avatar generation. Proc. AAAI Confer. Artif. Intell. 39(8), 8132\u20138140 (2025)","DOI":"10.1609\/aaai.v39i8.32877"},{"key":"4494_CR23","doi-asserted-by":"crossref","unstructured":"Guo, Z., Lee, Y.Y., Liu, J., Ben-Shabat, Y., Zordan, V., Kapadia, M.: Stylemotif: multi-modal motion stylization using style-content cross fusion. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 13349\u201313359 (2025)","DOI":"10.1109\/ICCV51701.2025.01240"},{"key":"4494_CR24","unstructured":"Li, Z., He, Y., Zhong, L., Shen, W., Zuo, Q., Qiu, L., Dong, Z., Yang, L.T., Yuan, W.: Mulsmo: multimodal stylized motion generation by bidirectional control flow. arXiv preprint arXiv:2412.09901 (2024)"},{"key":"4494_CR25","doi-asserted-by":"crossref","unstructured":"Sawdayee, H., Guo, C., Tevet, G., Zhou, B., Wang, J., Bermano, A.H.: Dance like a chicken: low-rank stylization for human motion diffusion. arXiv preprint arXiv:2503.19557 (2025)","DOI":"10.1111\/cgf.70365"},{"issue":"2","key":"4494_CR26","doi-asserted-by":"publisher","first-page":"1593","DOI":"10.1109\/TVCG.2025.3620400","volume":"32","author":"Y Wang","year":"2026","unstructured":"Wang, Y., Mo, H., Gao, C.: DiFusion: flexible stylized motion generation using digest-and-fusion scheme. IEEE Trans. Vis. Comput. Graph. 32(2), 1593\u20131604 (2026)","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"4494_CR27","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1007\/978-3-031-73232-4_23","volume-title":"Computer Vision\u2014ECCV 2024","author":"L Zhong","year":"2025","unstructured":"Zhong, L., Xie, Y., Jampani, V., Sun, D., Jiang, H.: SMooDi: stylized motion diffusion model. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) Computer Vision\u2014ECCV 2024, vol. 15059, pp. 405\u2013421. Springer Nature Switzerland, Cham (2025)"},{"key":"4494_CR28","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), Paris, France, pp. 3813\u20133824. IEEE (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"4494_CR29","doi-asserted-by":"crossref","unstructured":"Cervantes, P., Sekikawa, Y., Sato, I., Shinoda, K.: Implicit neural representations for variable length human motion generation. In: Avidan, S., Brostow, G., Ciss\u00e9, M. , Farinella, G.M., Hassner (eds.) Computer Vision\u2014ECCV 2022, vol. 13677, pp. 356\u2013372. Springer Nature Switzerland, Cham (2022)","DOI":"10.1007\/978-3-031-19790-1_22"},{"key":"4494_CR30","doi-asserted-by":"crossref","unstructured":"Degardin, B., Neves, J., Lopes, V., Brito, J., Yaghoubi, E., Proen a, H.: Generative adversarial graph convolutional networks for human action synthesis. In: 2022 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, USA, pp. 2753\u20132762. IEEE (2022)","DOI":"10.1109\/WACV51458.2022.00281"},{"key":"4494_CR31","doi-asserted-by":"crossref","unstructured":"Guo, C., Zuo, X., Wang, S., Zou, S., Sun, Q., Deng, A., Gong, M., Cheng, L.: Action2Motion: conditioned generation of 3D human motions. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 2021\u20132029 (2020)","DOI":"10.1145\/3394171.3413635"},{"key":"4494_CR32","doi-asserted-by":"crossref","unstructured":"Lu, Q., Zhang, Y., Lu, M., Roychowdhury, V.: Action-conditioned on-demand motion generation. In: Proceedings of the 30th ACM International Conference on Multimedia, Lisboa, Portugal, pp. 2249\u20132257. ACM (2022)","DOI":"10.1145\/3503161.3548287"},{"key":"4494_CR33","doi-asserted-by":"crossref","unstructured":"Athanasiou, N., Petrovich, M., Black, M.J., Varol, G.: SINC: spatial composition of 3D human motions for simultaneous action generation. In: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), Paris, France, pp. 9950\u20139961. IEEE (2023)","DOI":"10.1109\/ICCV51070.2023.00916"},{"key":"4494_CR34","doi-asserted-by":"crossref","unstructured":"Athanasiou, N., Petrovich, M., Black, M.J., Varol, G.: TEACH: temporal action composition for 3D humans. In: 2022 International Conference on 3D Vision (3DV), pp. 414\u2013423 (2022)","DOI":"10.1109\/3DV57658.2022.00053"},{"key":"4494_CR35","doi-asserted-by":"crossref","unstructured":"Barquero, G., Escalera, S., Palmero, C.: Seamless human motion composition with blended positional encodings. In: 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, pp. 457\u2013469. IEEE (2024)","DOI":"10.1109\/CVPR52733.2024.00051"},{"issue":"1","key":"4494_CR36","first-page":"1231","volume":"37","author":"T Lee","year":"2023","unstructured":"Lee, T., Moon, G., Lee, K.M.: Multiact: long-term 3d Human motion generation from multiple action labels. Proc. AAAI Confer. Artif. Intell. 37(1), 1231\u20131239 (2023)","journal-title":"Proc. AAAI Confer. Artif. Intell."},{"key":"4494_CR37","doi-asserted-by":"crossref","unstructured":"Li, S., Zhuang, S., Song, W., Zhang, X., Chen, H., Hao, A.: Sequential texts driven cohesive motions synthesis with natural transitions. In: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), Paris, France, pp. 9464\u20139474. IEEE (2023)","DOI":"10.1109\/ICCV51070.2023.00871"},{"key":"4494_CR38","doi-asserted-by":"crossref","unstructured":"Hassan, M., Ghosh, P., Tesch, J., Tzionas, D., Black, M.J.: Populating 3D scenes by learning human-scene interaction. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA, pp. 14703\u201314713. IEEE (2021)","DOI":"10.1109\/CVPR46437.2021.01447"},{"key":"4494_CR39","doi-asserted-by":"crossref","unstructured":"Huang, S., Wang, Z., Li, P., Jia, B., Liu, T., Zhu, Y., Liang, W., Zhu, S.C.: Diffusion-based generation, optimization, and planning in 3D scenes. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada, pp. 16750\u201316761. IEEE (2023)","DOI":"10.1109\/CVPR52729.2023.01607"},{"key":"4494_CR40","doi-asserted-by":"crossref","unstructured":"Hwang, I., Zhou, B., Kim, Y.M., Wang, J., Guo, C.: Scenemi: motion in-betweening for modeling human-scene interaction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 6034\u20136045 (2025)","DOI":"10.1109\/ICCV51701.2025.00570"},{"key":"4494_CR41","doi-asserted-by":"crossref","unstructured":"Cai, Z., Jiang, J., Qing, Z., Guo, X., Zhang, M., Lin, Z., Mei, H., Wei, C., Wang, R., Yin, W., Pan, L.: Digital life project: autonomous 3D characters with social intelligence. In: 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, pp. 582\u2013592. IEEE (2024)","DOI":"10.1109\/CVPR52733.2024.00062"},{"key":"4494_CR42","doi-asserted-by":"crossref","unstructured":"Chopin, B., Tang, H., Daoudi, M.: Bipartite graph diffusion model for human interaction generation. In: 2024 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, USA, pp. 5321\u20135330. IEEE (2024)","DOI":"10.1109\/WACV57701.2024.00525"},{"issue":"9","key":"4494_CR43","doi-asserted-by":"publisher","first-page":"3463","DOI":"10.1007\/s11263-024-02042-6","volume":"132","author":"H Liang","year":"2024","unstructured":"Liang, H., Zhang, W., Li, W., Jingyi, Yu., Lan, X.: InterGen: diffusion-based multi-human motion generation under complex interactions. Int. J. Comput. Vis. 132(9), 3463\u20133483 (2024)","journal-title":"Int. J. Comput. Vis."},{"key":"4494_CR44","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1007\/978-3-031-73195-2_2","volume-title":"Computer Vision\u2013ECCV 2024","author":"S Dai","year":"2025","unstructured":"Dai, S., Li, W., Sun, H., Huang, H., Ma, C., Huang, H., Kai, X., Ruizhen, H.: InterFusion: text-driven generation of 3D human-object interaction. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) Computer Vision\u2013ECCV 2024, vol. 15106, pp. 18\u201335. Springer Nature Switzerland, Cham (2025)"},{"key":"4494_CR45","doi-asserted-by":"crossref","unstructured":"Diller, C., Dai, A.: Cg-hoi: contact-guided 3d human-object interaction generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 19888\u201319901 (2024)","DOI":"10.1109\/CVPR52733.2024.01880"},{"key":"4494_CR46","doi-asserted-by":"crossref","unstructured":"Gao, J., Wang, Z., Xiao, Z., Wang, J., Wang, T., Cao, J., Hu, X., Liu, S., Dai, J., Pang, J.: Coohoi: learning cooperative human-object interaction with manipulated object dynamics. In: Advances in neural information processing systems (NeurIPS), vol. 37, pp. 79741\u201379763. Spotlight Presentation (2024)","DOI":"10.52202\/079017-2532"},{"key":"4494_CR47","doi-asserted-by":"crossref","unstructured":"Peng, X., Xie, Y., Wu, Z., Jampani, V., Sun, D., Jiang, H.: Hoi-diff: text-driven synthesis of 3d human-object interactions using diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pp. 2903\u20132913 (2025)","DOI":"10.1109\/CVPRW67362.2025.00271"},{"issue":"2","key":"4494_CR48","first-page":"1272","volume":"36","author":"B Li","year":"2022","unstructured":"Li, B., Zhao, Y., Zhelun, S., Sheng, L.: DanceFormer: music conditioned 3D dance generation with parametric motion transformer. Proc. AAAI Confer. Artif. Intell. 36(2), 1272\u20131279 (2022)","journal-title":"Proc. AAAI Confer. Artif. Intell."},{"key":"4494_CR49","doi-asserted-by":"crossref","unstructured":"Tseng, J., Castellon, R., Liu, C.K.: EDGE: editable dance generation from music. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada, pp. 448\u2013458. IEEE (2023)","DOI":"10.1109\/CVPR52729.2023.00051"},{"key":"4494_CR50","unstructured":"Wang, Q., Yang, X., Dong, Y., Govindaraj, N.R., Slabaugh, G., Yuan, S.: Dancechat: large language model-guided music-to-dance generation (2025)"},{"key":"4494_CR51","doi-asserted-by":"crossref","unstructured":"Chen, B., Li, Y., Ding, Y.-X., Shao, T., Zhou, K.: Enabling synergistic full-body control in prompt-based co-speech motion generation. In: Proceedings of the 32nd ACM International Conference on Multimedia, Melbourne, VIC Australia, pp. 6774\u20136783. ACM (2024)","DOI":"10.1145\/3664647.3680847"},{"key":"4494_CR52","doi-asserted-by":"crossref","unstructured":"Chhatre, K., Athanasiou, N., Becherini, G., Peters, C., Black, M.J., Bolkart, T.: Emotional speech-driven 3D body animation via disentangled latent diffusion. In: 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, pp. 1942\u20131953. IEEE (2024)","DOI":"10.1109\/CVPR52733.2024.00190"},{"issue":"9","key":"4494_CR53","first-page":"1","volume":"31","author":"Z Wu","year":"2024","unstructured":"Wu, Z., Wang, Q., Zheng, X., Ye, J., Yang, P., Wang, Y., Wang, Y.: Doodle your motion: sketch-guided human motion generation. IEEE Trans. Vis. Comput. Graph. 31(9), 1\u201311 (2024)","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"4494_CR54","doi-asserted-by":"crossref","unstructured":"Wang, T., Wu, Z., He, Q., Chu, J., Qian, L., Cheng, Y., Xing, J., Zhao, J., Jin, L.: Stickmotion: generating 3d human motions by drawing a stickman. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12370\u201312379 (2025)","DOI":"10.1109\/CVPR52734.2025.01154"},{"key":"4494_CR55","doi-asserted-by":"crossref","unstructured":"Zhong, L., Guo, C., Xie, Y., Wang, J., Li, C.: Sketch2anim: towards transferring sketch storyboards into 3d animation. arXiv preprint arXiv:2504.19189 (2025)","DOI":"10.1145\/3731167"},{"key":"4494_CR56","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., Polosukhin, I.: Attention is all you need"},{"key":"4494_CR57","unstructured":"Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y: Generative adversarial nets. In: Advances in Neural Information Processing Systems, vol. 27. Curran Associates, Inc. (2014)"},{"key":"4494_CR58","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. arXiv preprint arXiv:2006.11239 (2020)"},{"key":"4494_CR59","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: International Conference on Learning Representations (ICLR) (2021)"},{"key":"4494_CR60","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. In: Advances in Neural Information Processing Systems, vol. 34, pp. 8780\u20138794. Curran Associates, Inc. (2021)"},{"key":"4494_CR61","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)"},{"key":"4494_CR62","doi-asserted-by":"crossref","unstructured":"Mahmood, N., Ghorbani, N., Troje, N.F., Pons-Moll, G., Black, M.J.: AMASS: archive of motion capture as surface shapes. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5442\u20135451 (2019)","DOI":"10.1109\/ICCV.2019.00554"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-026-04494-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-026-04494-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-026-04494-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T11:42:50Z","timestamp":1779363770000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-026-04494-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":62,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2026,5]]}},"alternative-id":["4494"],"URL":"https:\/\/doi.org\/10.1007\/s00371-026-04494-y","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]},"assertion":[{"value":"7 March 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 May 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval and consent to participate"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The supplementary material will be provided with this submission.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Materials availability"}}],"article-number":"284"}}