{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T14:55:06Z","timestamp":1776696906395,"version":"3.51.2"},"reference-count":49,"publisher":"Association for Computing Machinery (ACM)","issue":"5","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["92470126, 62276139, and U24B20155"],"award-info":[{"award-number":["92470126, 62276139, and U24B20155"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Qinglan Project of Jiangsu Province of China, and Jiangsu Provincial Science and Technology","award":["BG2024042"],"award-info":[{"award-number":["BG2024042"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2026,5,31]]},"abstract":"<jats:p>Generating natural and realistic human motion sequences under the constraints of 3D scenes is a highly challenging task, requiring not only the precise modeling of dynamic variations in human joints but also the rigorous consideration of intricate interactions between the human body and the surrounding environment. While recent advances in deep generative models show great potential in tackling these challenges, existing methods often result in unnatural human motions and human\u2013environment penetration during generation. In order to cope with these issues, we propose a novel approach that divides human motion generation into two stages. The first stage employs a bidirectional long short-term memory network incorporated with full-connected layers to generate motion trajectory under the input conditions including the starting and ending positions and orientations of the human model and scene feature point clouds extracted from the surrounding environment. In the second stage, we design a conditional diffusion model, guided by the trajectory generated in the first stage and  the embedding of 3D scene information, to generate human motion sequences within 3D scenes. We evaluate our framework through extensive experiments on the PROX datasets, which validates its effectiveness. The results show that our method significantly outperforms existing ones in enhancing human motion naturalness and reasonableness, and reducing human penetration.<\/jats:p>","DOI":"10.1145\/3789508","type":"journal-article","created":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T14:49:43Z","timestamp":1774968583000},"page":"1-19","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["3D Scenes Motion Planning and Generation with Motion Diffusion Probabilistic Model"],"prefix":"10.1145","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-1046-8953","authenticated-orcid":false,"given":"Jiawei","family":"Huang","sequence":"first","affiliation":[{"name":"School of Software, Nanjing University of Information Science and Technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0462-3729","authenticated-orcid":false,"given":"Yubao","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Computer Science, Nanjing University of Information Science and Technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4909-0361","authenticated-orcid":false,"given":"Guiyu","family":"Xia","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Nanjing University of Information Science and Technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8161-1780","authenticated-orcid":false,"given":"Qingshan","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4846-2015","authenticated-orcid":false,"given":"Mohan","family":"Kankanhalli","sequence":"additional","affiliation":[{"name":"School of Computing, National University of Singapore, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,4,20]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.110"},{"key":"e_1_3_1_3_2","unstructured":"Jimmy Ba Jamie Kiros and Geoffrey E. Hinton. 2016. Layer normalization. arXiv:1607.06450. Retrieved from https:\/\/arxiv.org\/abs\/1607.06450"},{"key":"e_1_3_1_4_2","unstructured":"Tom B. Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et\u00a0al. 2020. Language models are few-shot learners. arXiv:2005.14165. Retrieved from https:\/\/arxiv.org\/abs\/2005.14165"},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0274-5"},{"key":"e_1_3_1_6_2","unstructured":"Yukang Cao Yan-Pei Cao Kai Han Ying Shan and Kwan-Yee K. Wong. 2023. DreamAvatar: Text-and-shape guided 3D human avatar generation via diffusion models. arXiv:2304.00916. Retrieved from https:\/\/arxiv.org\/abs\/2304.00916"},{"key":"e_1_3_1_7_2","unstructured":"Zhe Cao. 2020. Long-term human motion prediction with scene context. arXiv:2007.03672. Retrieved from https:\/\/arxiv.org\/abs\/2007.03672"},{"key":"e_1_3_1_8_2","first-page":"2200","volume-title":"IEEE International Conference on Computer Vision","author":"de Almeida T. R.","year":"2023","unstructured":"T. R. de Almeida, A. Rudenko, T. Schreiter, Y. Zhu, E. G. Maestro, L. Morillo-Mendez, T. P. Kucner, O. M. Mozos, M. Magnusson, L. Palmieri, et\u00a0al. 2023. THOR-Magni: Comparative analysis of deep learning models for role-conditioned human motion prediction. In IEEE International Conference on Computer Vision, 2200\u20132209."},{"key":"e_1_3_1_9_2","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et\u00a0al. 2021. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv:2010.11929. Retrieved from https:\/\/arxiv.org\/abs\/2010.11929"},{"key":"e_1_3_1_10_2","doi-asserted-by":"crossref","unstructured":"Anindita Ghosh Rishabh Dabral Vladislav Golyanik Christian Theobalt and Philipp Slusallek. 2022. IMoS: Intent-driven full-body motion synthesis for human-object interactions. In Computer Graphics Forum.","DOI":"10.1111\/cgf.14739"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.3390\/s25082409"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00240"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw.2009.5206859"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.01118"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1103\/physreve.51.4282"},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","unstructured":"J. Ho A. Jain and P. Abbeel. 2020. Denoising diffusion probabilistic models. arXiv:2006.11239. Retrieved from 10.48550\/arXiv.2006.11239","DOI":"10.48550\/arXiv.2006.11239"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_1_19_2","unstructured":"Yihan Hu Siqi Chai Zhening Yang Jingyu Qian Kun Li Wenxin Shao Haichao Zhang Wei Xu and Qiang Liu. 2024. Solving motion planning tasks with a scalable generative model. arXiv:2407.02797. Retrieved from https:\/\/arxiv.org\/abs\/2407.02797"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2013.248"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/SCORED.2003.1459684"},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00171"},{"key":"e_1_3_1_23_2","doi-asserted-by":"crossref","unstructured":"Korrawe Karunratanakul Konpat Preechakul Supasorn Suwajanakorn and Siyu Tang. 2023. Guided motion diffusion for controllable human motion synthesis. In International Conference on Computer Vision.","DOI":"10.1109\/ICCV51070.2023.00205"},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/2601097.2601117"},{"key":"e_1_3_1_25_2","unstructured":"Diederik P. Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv:1412.06980. Retrieved from https:\/\/arxiv.org\/abs\/1412.6980"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33765-9_15"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2010.5540140"},{"key":"e_1_3_1_28_2","doi-asserted-by":"crossref","unstructured":"Jiye Lee and Hanbyul Joo. 2023. Locomotion-action-manipulation: Synthesizing human-scene interactions in complex 3D environments. In International Conference on Computer Vision.","DOI":"10.1109\/ICCV51070.2023.00886"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2007.01089.x"},{"key":"e_1_3_1_30_2","unstructured":"Liunian Harold Li Mark Yatskar Da Yin Cho-Jui Hsieh and Kai-Wei Chang. 2019. VisualBERT: A simple and performant baseline for vision and language. arXiv:1908.03557. Retrieved from https:\/\/arxiv.org\/abs\/1908.03557"},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00554"},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00731"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01443"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_21"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.01123"},{"key":"e_1_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2009.5459260"},{"key":"e_1_3_1_37_2","doi-asserted-by":"crossref","unstructured":"Hao-Yang Peng Jia-Peng Zhang Meng-Hao Guo Yan-Pei Cao and Shi-Min Hu. 2024. CharacterGen: Efficient 3D character generation from single images with multi-view pose canonicalization. arXiv:2402.17214. Retrieved from https:\/\/arxiv.org\/abs\/2402.17214","DOI":"10.1145\/3658217"},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2008.4587520"},{"key":"e_1_3_1_39_2","doi-asserted-by":"crossref","unstructured":"Lei Tai Jingwei Zhang Ming Liu and Wolfram Burgard. 2017. Socially compliant navigation through raw depth inputs with generative adversarial imitation learning. In IEEE International Conference on Robotics and Automation.","DOI":"10.1109\/ICRA.2018.8460968"},{"key":"e_1_3_1_40_2","unstructured":"G. Tevet S. Raab B. Gordon Y. Shafir A. H. Bermano and D. Cohen-Or. 2022. Human motion diffusion model. arXiv:2209.14916. Retrieved from https:\/\/arxiv.org\/abs\/2209.14916"},{"key":"e_1_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/1141911.1142008"},{"key":"e_1_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2012.61"},{"key":"e_1_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2000.855813"},{"key":"e_1_3_1_44_2","unstructured":"Zhutian Yang Caelan Garrett Dieter Fox Tom\u00e1s Lozano-P\u00e9rez and Leslie Pack Kaelbling. 2024. Guiding long-horizon task and motion planning with vision language models. arXiv:2410.02193. Retrieved from https:\/\/arxiv.org\/abs\/2410.02193"},{"key":"e_1_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.002"},{"key":"e_1_3_1_46_2","unstructured":"Jiaxu Zhang Shaoli Huang Zhigang Tu Xin Chen Xiaohang Zhan Gang Yu and Ying Shan. 2023. TapMo: Shape-aware motion generation of skeleton-free characters. arXiv:2310.12678. Retrieved from https:\/\/arxiv.org\/abs\/2310.12678"},{"key":"e_1_3_1_47_2","unstructured":"Xiangyue Zhang Jianfang Li Jiaxu Zhang Ziqiang Dang Jianqiang Ren Liefeng Bo and Zhigang Tu. 2025. SemTalk: Holistic co-speech motion generation with frame-level semantic emphasis. arXiv:2412.16563. Retrieved from https:\/\/arxiv.org\/abs\/2412.16563"},{"key":"e_1_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00623"},{"key":"e_1_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2004.73"},{"key":"e_1_3_1_50_2","doi-asserted-by":"crossref","unstructured":"Yufei Zhu Andrey Rudenko Tomasz P. Kucner Luigi Palmieri Kai O. Arras Achim J. Lilienthal and Martin Magnusson. 2023. CLiFF-LHMP: Using spatial dynamics patterns for long-term human motion prediction. In International Conference on Intelligent Robots and Systems.","DOI":"10.1109\/IROS55552.2023.10342031"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3789508","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T14:11:01Z","timestamp":1776694261000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3789508"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,20]]},"references-count":49,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,5,31]]}},"alternative-id":["10.1145\/3789508"],"URL":"https:\/\/doi.org\/10.1145\/3789508","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"value":"1551-6857","type":"print"},{"value":"1551-6865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,20]]},"assertion":[{"value":"2025-06-04","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-11-05","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-04-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}