{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T16:37:40Z","timestamp":1781714260687,"version":"3.54.5"},"publisher-location":"Cham","reference-count":51,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031733963","type":"print"},{"value":"9783031733970","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"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":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-73397-0_19","type":"book-chapter","created":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T19:05:28Z","timestamp":1730574328000},"page":"324-341","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["Optimizing Diffusion Models for\u00a0Joint Trajectory Prediction and\u00a0Controllable Generation"],"prefix":"10.1007","author":[{"given":"Yixiao","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lingfeng","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Simone","family":"Rossi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yichen","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chensheng","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas","family":"Hannagan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stefano","family":"Sabatini","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicola","family":"Poerio","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masayoshi","family":"Tomizuka","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Zhan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,3]]},"reference":[{"key":"19_CR1","doi-asserted-by":"crossref","unstructured":"Avrahami, O., Lischinski, D., Fried, O.: Blended diffusion for text-driven editing of natural images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18208\u201318218 (2022)","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"19_CR2","doi-asserted-by":"crossref","unstructured":"Cheng, J., Mei, X., Liu, M.: Forecast-MAE: self-supervised pre-training for motion forecasting with masked autoencoders. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8679\u20138689 (2023)","DOI":"10.1109\/ICCV51070.2023.00797"},{"key":"19_CR3","doi-asserted-by":"crossref","unstructured":"Chung, H., Sim, B., Ye, J.C.: Come-closer-diffuse-faster: accelerating conditional diffusion models for inverse problems through stochastic contraction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12413\u201312422 (2022)","DOI":"10.1109\/CVPR52688.2022.01209"},{"key":"19_CR4","first-page":"8780","volume":"34","author":"P Dhariwal","year":"2021","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. Adv. Neural. Inf. Process. Syst. 34, 8780\u20138794 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"4","key":"19_CR5","doi-asserted-by":"publisher","first-page":"633","DOI":"10.3390\/e25040633","volume":"25","author":"G Franzese","year":"2023","unstructured":"Franzese, G., et al.: How much is enough? A study on diffusion times in score-based generative models. Entropy 25(4), 633 (2023)","journal-title":"Entropy"},{"issue":"5","key":"19_CR6","doi-asserted-by":"publisher","first-page":"2946","DOI":"10.1109\/LRA.2023.3262150","volume":"8","author":"X Gao","year":"2023","unstructured":"Gao, X., Jia, X., Li, Y., Xiong, H.: Dynamic scenario representation learning for motion forecasting with heterogeneous graph convolutional recurrent networks. IEEE Robot. Autom. Lett. 8(5), 2946\u20132953 (2023)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"19_CR7","unstructured":"Gilles, T., Sabatini, S., Tsishkou, D., Stanciulescu, B., Moutarde, F.: THOMAS: trajectory heatmap output with learned multi-agent sampling. arXiv preprint arXiv:2110.06607 (2021)"},{"key":"19_CR8","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672\u20132680 (2014)"},{"key":"19_CR9","doi-asserted-by":"crossref","unstructured":"Gu, J., Sun, C., Zhao, H.: DenseTNT: end-to-end trajectory prediction from dense goal sets. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15303\u201315312 (2021)","DOI":"10.1109\/ICCV48922.2021.01502"},{"key":"19_CR10","doi-asserted-by":"crossref","unstructured":"Gu, T., et al.: Stochastic trajectory prediction via motion indeterminacy diffusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17113\u201317122 (2022)","DOI":"10.1109\/CVPR52688.2022.01660"},{"key":"19_CR11","unstructured":"Guo, Z., Gao, X., Zhou, J., Cai, X., Shi, B.: SceneDM: scene-level multi-agent trajectory generation with consistent diffusion models. arXiv preprint arXiv:2311.15736 (2023)"},{"key":"19_CR12","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"19_CR13","unstructured":"Ho, J., Salimans, T., Gritsenko, A., Chan, W., Norouzi, M., Fleet, D.J.: Video diffusion models (2022)"},{"key":"19_CR14","unstructured":"Hyv\u00e4rinen, A., Dayan, P.: Estimation of non-normalized statistical models by score matching. J. Mach. Learn. Res. 6(4) (2005)"},{"key":"19_CR15","unstructured":"Janner, M., Du, Y., Tenenbaum, J.B., Levine, S.: Planning with diffusion for flexible behavior synthesis. arXiv preprint arXiv:2205.09991 (2022)"},{"key":"19_CR16","doi-asserted-by":"crossref","unstructured":"Jiang, C., Cornman, A., Park, C., Sapp, B., Zhou, Y., Anguelov, D., et\u00a0al.: MotionDiffuser: controllable multi-agent motion prediction using diffusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9644\u20139653 (2023)","DOI":"10.1109\/CVPR52729.2023.00930"},{"key":"19_CR17","first-page":"21696","volume":"34","author":"D Kingma","year":"2021","unstructured":"Kingma, D., Salimans, T., Poole, B., Ho, J.: Variational diffusion models. Adv. Neural. Inf. Process. Syst. 34, 21696\u201321707 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"19_CR18","unstructured":"Lan, Z., et al.: SEPT: towards efficient scene representation learning for motion prediction. arXiv preprint arXiv:2309.15289 (2023)"},{"issue":"3","key":"19_CR19","doi-asserted-by":"publisher","first-page":"932","DOI":"10.1016\/j.ejor.2004.08.029","volume":"169","author":"M Laumanns","year":"2006","unstructured":"Laumanns, M., Thiele, L., Zitzler, E.: An efficient, adaptive parameter variation scheme for metaheuristics based on the epsilon-constraint method. Eur. J. Oper. Res. 169(3), 932\u2013942 (2006)","journal-title":"Eur. J. Oper. Res."},{"key":"19_CR20","unstructured":"Lin, H., Wang, Y., Huo, M., Peng, C., Liu, Z., Tomizuka, M.: Joint pedestrian trajectory prediction through posterior sampling. arXiv preprint arXiv:2404.00237 (2024)"},{"key":"19_CR21","first-page":"5775","volume":"35","author":"C Lu","year":"2022","unstructured":"Lu, C., Zhou, Y., Bao, F., Chen, J., Li, C., Zhu, J.: DPM-Solver: a fast ode solver for diffusion probabilistic model sampling in around 10 steps. Adv. Neural. Inf. Process. Syst. 35, 5775\u20135787 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"19_CR22","doi-asserted-by":"crossref","unstructured":"Luo, S., Hu, W.: Diffusion probabilistic models for 3D point cloud generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2837\u20132845 (2021)","DOI":"10.1109\/CVPR46437.2021.00286"},{"key":"19_CR23","unstructured":"Meng, C., et al.: SDEdit: guided image synthesis and editing with stochastic differential equations. arXiv preprint arXiv:2108.01073 (2022)"},{"key":"19_CR24","doi-asserted-by":"crossref","unstructured":"Nayakanti, N., Al-Rfou, R., Zhou, A., Goel, K., Refaat, K.S., Sapp, B.: Wayformer: motion forecasting via simple and efficient attention networks. In: 2023 IEEE International Conference on Robotics and Automation (ICRA), pp. 2980\u20132987. IEEE (2023)","DOI":"10.1109\/ICRA48891.2023.10160609"},{"key":"19_CR25","unstructured":"Ngiam, J., et\u00a0al.: Scene transformer: a unified architecture for predicting multiple agent trajectories. arXiv preprint arXiv:2106.08417 (2021)"},{"key":"19_CR26","doi-asserted-by":"crossref","unstructured":"Peng, C., et al.: Delflow: dense efficient learning of scene flow for large-scale point clouds. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 16901\u201316910 (2023)","DOI":"10.1109\/ICCV51070.2023.01550"},{"key":"19_CR27","unstructured":"Peng, C., et al.: Q-SLAM: quadric representations for monocular slam. arXiv preprint arXiv:2403.08125 (2024)"},{"key":"19_CR28","doi-asserted-by":"crossref","unstructured":"Rempe, D., et al.: Trace and pace: controllable pedestrian animation via guided trajectory diffusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13756\u201313766 (2023)","DOI":"10.1109\/CVPR52729.2023.01322"},{"key":"19_CR29","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"19_CR30","doi-asserted-by":"crossref","unstructured":"Rowe, L., Ethier, M., Dykhne, E.H., Czarnecki, K.: FJMP: factorized joint multi-agent motion prediction over learned directed acyclic interaction graphs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13745\u201313755 (2023)","DOI":"10.1109\/CVPR52729.2023.01321"},{"key":"19_CR31","unstructured":"Salimans, T., Ho, J.: Progressive distillation for fast sampling of diffusion models. arXiv preprint arXiv:2202.00512 (2022)"},{"key":"19_CR32","unstructured":"San-Roman, R., Nachmani, E., Wolf, L.: Noise estimation for generative diffusion models. arXiv preprint arXiv:2104.02600 (2021)"},{"key":"19_CR33","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1007\/BF00934527","volume":"39","author":"HD Sherali","year":"1983","unstructured":"Sherali, H.D., Soyster, A.L.: Preemptive and nonpreemptive multi-objective programming: relationship and counterexamples. J. Optim. Theory Appl. 39, 173\u2013186 (1983)","journal-title":"J. Optim. Theory Appl."},{"key":"19_CR34","doi-asserted-by":"crossref","unstructured":"Shi, S., Jiang, L., Dai, D., Schiele, B.: MTR++: multi-agent motion prediction with symmetric scene modeling and guided intention querying. arXiv preprint arXiv:2306.17770 (2023)","DOI":"10.1109\/TPAMI.2024.3352811"},{"key":"19_CR35","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)"},{"key":"19_CR36","unstructured":"Song, J., Vahdat, A., Mardani, M., Kautz, J.: Pseudoinverse-guided diffusion models for inverse problems. In: International Conference on Learning Representations (2022)"},{"key":"19_CR37","unstructured":"Song, Y., Dhariwal, P., Chen, M., Sutskever, I.: Consistency models. arXiv preprint arXiv:2303.01469 (2023)"},{"key":"19_CR38","unstructured":"Song, Y., Ermon, S.: Generative modeling by estimating gradients of the data distribution. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"key":"19_CR39","unstructured":"Song, Y., Sohl-Dickstein, J., Kingma, D.P., Kumar, A., Ermon, S., Poole, B.: Score-based generative modeling through stochastic differential equations. arXiv preprint arXiv:2011.13456 (2020)"},{"key":"19_CR40","doi-asserted-by":"crossref","unstructured":"Sun, Q., Huang, X., Gu, J., Williams, B.C., Zhao, H.: M2I: from factored marginal trajectory prediction to interactive prediction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6543\u20136552 (2022)","DOI":"10.1109\/CVPR52688.2022.00643"},{"key":"19_CR41","doi-asserted-by":"crossref","unstructured":"Suo, S., Regalado, S., Casas, S., Urtasun, R.: TrafficSim: learning to simulate realistic multi-agent behaviors. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10400\u201310409 (2021)","DOI":"10.1109\/CVPR46437.2021.01026"},{"key":"19_CR42","doi-asserted-by":"crossref","unstructured":"Varadarajan, B., et\u00a0al.: MultiPath++: efficient information fusion and trajectory aggregation for behavior prediction. In: 2022 International Conference on Robotics and Automation (ICRA), pp. 7814\u20137821. IEEE (2022)","DOI":"10.1109\/ICRA46639.2022.9812107"},{"key":"19_CR43","unstructured":"Watson, D., Chan, W., Ho, J., Norouzi, M.: Learning fast samplers for diffusion models by differentiating through sample quality. arXiv preprint arXiv:2202.05830 (2022)"},{"key":"19_CR44","unstructured":"Wilson, B., et\u00a0al.: Argoverse 2: next generation datasets for self-driving perception and forecasting. arXiv preprint arXiv:2301.00493 (2023)"},{"key":"19_CR45","doi-asserted-by":"crossref","unstructured":"Xu, D., Chen, Y., Ivanovic, B., Pavone, M.: BITS: bi-level imitation for traffic simulation. In: 2023 IEEE International Conference on Robotics and Automation (ICRA), pp. 2929\u20132936. IEEE (2023)","DOI":"10.1109\/ICRA48891.2023.10161167"},{"key":"19_CR46","unstructured":"Zhang, Q., Chen, Y.: Fast sampling of diffusion models with exponential integrator. arXiv preprint arXiv:2204.13902 (2022)"},{"key":"19_CR47","unstructured":"Zhao, et\u00a0al.: TNT: target-driven trajectory prediction. In: Conference on Robot Learning, pp. 895\u2013904. PMLR (2021)"},{"key":"19_CR48","unstructured":"Zheng, H., He, P., Chen, W., Zhou, M.: Truncated diffusion probabilistic models. arXiv preprint arXiv:2202.09671 (2022)"},{"key":"19_CR49","doi-asserted-by":"crossref","unstructured":"Zhong, Z., et al.: Guided conditional diffusion for controllable traffic simulation. In: 2023 IEEE International Conference on Robotics and Automation (ICRA), pp. 3560\u20133566. IEEE (2023)","DOI":"10.1109\/ICRA48891.2023.10161463"},{"key":"19_CR50","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Wang, J., Li, Y.H., Huang, Y.K.: Query-centric trajectory prediction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17863\u201317873 (2023)","DOI":"10.1109\/CVPR52729.2023.01713"},{"key":"19_CR51","unstructured":"Zhou, Z., Wen, Z., Wang, J., Li, Y.H., Huang, Y.K.: QCNeXt: a next-generation framework for joint multi-agent trajectory prediction (2023)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73397-0_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T19:20:33Z","timestamp":1730575233000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73397-0_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,3]]},"ISBN":["9783031733963","9783031733970"],"references-count":51,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73397-0_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,3]]},"assertion":[{"value":"3 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}