{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T11:08:40Z","timestamp":1789038520276,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032373618","type":"print"},{"value":"9783032373625","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-37362-5_35","type":"book-chapter","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T10:17:41Z","timestamp":1789035461000},"page":"645-663","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Trajectory Forcing: Structure-First Generation with\u00a0Controllable Semantic Trajectories"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-6310-5701","authenticated-orcid":false,"given":"Merve","family":"Kocabas","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6918-2928","authenticated-orcid":false,"given":"Gege","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8177-0925","authenticated-orcid":false,"given":"Bernhard","family":"Sch\u00f6lkopf","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8151-3726","authenticated-orcid":false,"given":"Andreas","family":"Geiger","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,11]]},"reference":[{"key":"35_CR1","unstructured":"Atanov, A., et al.: VideoFlexTok: flexible-length coarse-to-fine video tokenization. In: Proc. of the International Conf. on Machine learning (ICML) (2026)"},{"key":"35_CR2","unstructured":"Baade, A., et al.: Latent forcing: reordering the diffusion trajectory for pixel-space image generation. arXiv preprint arXiv:2602.11401 (2026)"},{"key":"35_CR3","unstructured":"Carion, N., et\u00a0al.: SAM 3: segment anything with concepts. arXiv preprint arXiv:2511.16719 (2025)"},{"key":"35_CR4","doi-asserted-by":"crossref","unstructured":"Chen, B., Mons\u00f3, D.M., Du, Y., Simchowitz, M., Tedrake, R., Sitzmann, V.: Diffusion forcing: next-token prediction meets full-sequence diffusion. In: Advances in Neural Information Processing Systems (NeurIPS) (2025)","DOI":"10.52202\/079017-0759"},{"key":"35_CR5","unstructured":"Chen, S., Ge, C., Zhang, S., Sun, P., Luo, P.: PixelFlow: pixel-space generative models with flow. arXiv preprint arXiv:2504.07963 (2025)"},{"key":"35_CR6","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"35_CR7","unstructured":"Deng, M., Li, H., Li, T., Du, Y., He, K.: Generative modeling via drifting. arXiv preprint arXiv:2602.04770 (2026)"},{"key":"35_CR8","doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R., Ommer, B.: Taming transformers for high-resolution image synthesis. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"35_CR9","unstructured":"Frans, K., Hafner, D., Levine, S., Abbeel, P.: One step diffusion via shortcut models. In: Proc. of the International Conf. on Learning Representations (ICLR) (2025)"},{"key":"35_CR10","unstructured":"Gao, G., Huang, H., Fu, C., He, R.: Causal representation learning for context-aware face transfer. arXiv preprint arXiv:2110.01571 (2021)"},{"key":"35_CR11","doi-asserted-by":"crossref","unstructured":"Gao, G., Liu, W., Chen, A., Geiger, A., Sch\u00f6lkopf, B.: GraphDreamer: compositional 3D scene synthesis from scene graphs. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.02012"},{"key":"35_CR12","unstructured":"Gao, G., Sch\u00f6lkopf, B., Geiger, A.: Slots, transitions, loops: learning composable world models for arc. arXiv preprint arXiv:2606.12316 (2026)"},{"key":"35_CR13","doi-asserted-by":"crossref","unstructured":"Geng, Z., Deng, M., Bai, X., Kolter, J.Z., He, K.: Mean flows for one-step generative modeling. In: Advances in Neural Information Processing Systems (NeurIPS) (2025)","DOI":"10.52202\/085713-2534"},{"key":"35_CR14","unstructured":"Geng, Z., Lu, Y., Wu, Z., Shechtman, E., Kolter, J.Z., He, K.: Improved mean flows: on the challenges of fastforward generative models. arXiv preprint arXiv:2512.02012 (2025)"},{"key":"35_CR15","unstructured":"Gupta, S., Jalal, A., Parulekar, A., Price, E., Xun, Z.: Diffusion posterior sampling is computationally intractable. In: Proc. of the International Conf. on Machine Learning (ICML) (2024)"},{"key":"35_CR16","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local nash equilibrium. In: Advances in Neural Information Processing Systems, NeurIPS (2017)"},{"key":"35_CR17","unstructured":"Hu, Z., Lai, C.H., Wu, G., Mitsufuji, Y., Ermon, S.: Meanflow transformers with representation autoencoders. arXiv preprint arXiv:2511.13019 (2025)"},{"key":"35_CR18","unstructured":"Jordan, K., et al.: Muon: an optimizer for hidden layers in neural networks (2024). https:\/\/kellerjordan.github.io\/posts\/muon"},{"key":"35_CR19","unstructured":"Kim, D., et al.: Consistency trajectory models: learning probability flow ODE trajectory of diffusion. In: Proc. of the International Conf. on Learning Representations (ICLR) (2024)"},{"key":"35_CR20","unstructured":"Lei, J., et al.: There is no VAE: advancing end-to-end pixel-space generative modeling via self-supervised pre-training. In: Proc. of the International Conf. on Learning Representations (ICLR) (2026)"},{"key":"35_CR21","unstructured":"Li, T., He, K.: Back to basics: let denoising generative models denoise. arXiv preprint arXiv:2511.13720 (2026)"},{"key":"35_CR22","doi-asserted-by":"crossref","unstructured":"Li, T., Tian, Y., Li, H., Deng, M., He, K.: Autoregressive image generation without vector quantization. In: Advances in Neural Information Processing Systems (NeurIPS) (2024)","DOI":"10.52202\/079017-1797"},{"key":"35_CR23","unstructured":"Li, Y., Bornschein, J., Chen, T.: Denoising autoregressive representation learning. In: Proc. of the International Conf. on Machine Learning (ICML) (2024)"},{"key":"35_CR24","unstructured":"Liu, X., Gong, C., Liu, Q.: Flow straight and fast: learning to generate and transfer data with rectified flow. arXiv preprint arXiv:2209.03003 (2022)"},{"key":"35_CR25","unstructured":"Lu, C., Song, Y.: Simplifying, stabilizing and scaling continuous-time consistency models. In: Proc. of the International Conf. on Learning Representations (ICLR) (2025)"},{"key":"35_CR26","unstructured":"Lu, Y., et al.: One-step latent-free image generation with pixel mean flows. arXiv preprint arXiv:2601.22158 (2026)"},{"key":"35_CR27","doi-asserted-by":"crossref","unstructured":"Ma, N., et al.: SIT: exploring flow and diffusion-based generative models with scalable interpolant transformers. In: European Conference on Computer Vision, pp. 23\u201340. Springer (2024)","DOI":"10.1007\/978-3-031-72980-5_2"},{"key":"35_CR28","unstructured":"Ma, Z., Wei, L., Wang, S., Zhang, S., Tian, Q.: DeCo: frequency-decoupled pixel diffusion for end-to-end image generation. arXiv preprint arXiv:2511.19365 (2025)"},{"key":"35_CR29","doi-asserted-by":"crossref","unstructured":"Meng, C., et al.: On distillation of guided diffusion models. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.01374"},{"key":"35_CR30","unstructured":"Oquab, M., et al.: DINOv2: learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"35_CR31","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. In: Proc. of the IEEE International Conf. on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"35_CR32","unstructured":"Ren, S., Yu, Q., He, J., Shen, X., Yuille, A., Chen, L.C.: FlowAR: scale-wise autoregressive image generation meets flow matching. arXiv preprint arXiv:2412.15205 (2024)"},{"key":"35_CR33","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"35_CR34","unstructured":"Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training GANs. In: Advances in Neural Information Processing Systems (NeurIPS) (2016)"},{"key":"35_CR35","unstructured":"Salimans, T., Ho, J.: Progressive distillation for fast sampling of diffusion models. In: Proc. of the International Conf. on Learning Representations (ICLR) (2022)"},{"key":"35_CR36","unstructured":"Song, Y., Dhariwal, P.: Improved techniques for training consistency models. In: Proc. of the International Conf. on Learning Representations (ICLR) (2024)"},{"key":"35_CR37","unstructured":"Song, Y., Dhariwal, P., Chen, M., Sutskever, I.: Consistency models. In: Proc. of the International Conf. on Machine learning (ICML) (2023)"},{"key":"35_CR38","doi-asserted-by":"crossref","unstructured":"Tian, K., Jiang, Y., Yuan, Z., PENG, B., Wang, L.: Visual autoregressive modeling: scalable image generation via next-scale prediction. In: Advances in Neural Information Processing Systems (NeurIPS) (2024)","DOI":"10.52202\/079017-2694"},{"key":"35_CR39","unstructured":"Venkataramanan, S., et al.: Franca: nested matryoshka clustering for scalable visual representation learning. arXiv preprint arXiv:2507.14137 (2025)"},{"key":"35_CR40","unstructured":"Wang, S., Gao, Z., Zhu, C., Huang, W., Wang, L.: PixNerd: pixel neural field diffusion. In: Proc. of the International Conf. on Learning Representations (ICLR) (2026)"},{"key":"35_CR41","unstructured":"Wang, Y., Wang, Z., Wu, Z., Tao, Q., Liao, K., Loy, C.C.: Next visual granularity generation. In: Proc. of the International Conf. on Learning Representations (ICLR) (2026)"},{"key":"35_CR42","unstructured":"Wang, Z., et al.: Transition models: rethinking the generative learning objective. arXiv preprint arXiv:2509.04394 (2025)"},{"key":"35_CR43","doi-asserted-by":"crossref","unstructured":"Wei, C., et al.: Diffusion models as masked autoencoders. In: Proc. of the IEEE International Conf. on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.01492"},{"key":"35_CR44","unstructured":"Yang, J., Geng, Z., Ju, X., Tian, Y., Wang, Y.: Representation Fr\u00e9chet loss for visual generation. arXiv preprint arXiv:2604.28190 (2026)"},{"key":"35_CR45","unstructured":"Yu, S., et al.: Representation alignment for generation: training diffusion transformers is easier than you think. In: Proc. of the International Conf. on Learning Representations (ICLR) (2025)"},{"key":"35_CR46","unstructured":"Zhang, H., et al.: AlphaFlow: understanding and improving meanflow models. arXiv preprint arXiv:2510.20771 (2025)"},{"key":"35_CR47","unstructured":"Zheng, B., Ma, N., Tong, S., Xie, S.: Diffusion transformers with representation autoencoders. In: Proc. of the International Conf. on Learning Representations (ICLR) (2026)"},{"key":"35_CR48","unstructured":"Zhou, L., Ermon, S., Song, J.: Inductive moment matching. In: Proc. of the International Conf. on Machine learning (ICML) (2025)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37362-5_35","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T10:18:03Z","timestamp":1789035483000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37362-5_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032373618","9783032373625"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37362-5_35","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"11 September 2026","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":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}