{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T11:07:16Z","timestamp":1789038436879,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":60,"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_19","type":"book-chapter","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T10:16:02Z","timestamp":1789035362000},"page":"351-369","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Test-Time Noise Guided Adaptation for\u00a0Realistic Autoregressive Video Generation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-4259-8249","authenticated-orcid":false,"given":"Dimitrios","family":"Karageorgiou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5441-7341","authenticated-orcid":false,"given":"Symeon","family":"Papadopoulos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6447-9020","authenticated-orcid":false,"given":"Ioannis","family":"Kompatsiaris","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8947-1332","authenticated-orcid":false,"given":"Efstratios","family":"Gavves","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,11]]},"reference":[{"key":"19_CR1","unstructured":"Agarwal, N., et\u00a0al.: Cosmos world foundation model platform for physical ai. arXiv preprint arXiv:2501.03575 (2025)"},{"key":"19_CR2","unstructured":"Ali, A., et\u00a0al.: World simulation with video foundation models for physical ai. arXiv preprint arXiv:2511.00062 (2025)"},{"key":"19_CR3","doi-asserted-by":"crossref","unstructured":"Bar-Tal, O., et al.: Lumiere: a space-time diffusion model for video generation. In: SIGGRAPH Asia 2024 Conference Papers, pp. 1\u201311 (2024)","DOI":"10.1145\/3680528.3687614"},{"key":"19_CR4","doi-asserted-by":"crossref","unstructured":"Blattmann, A., Rombach, R., Ling, H., Dockhorn, T., Kim, S.W., Fidler, S., Kreis, K.: Align your latents: high-resolution video synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22563\u201322575 (2023)","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"19_CR5","unstructured":"Brooks, T., et al.: Video generation models as world simulators (2024). https:\/\/openai.com\/index\/video-generation-models-as-world-simulators\/"},{"key":"19_CR6","unstructured":"Chen, G., et\u00a0al.: Skyreels-v2: infinite-length film generative model. arXiv preprint arXiv:2504.13074 (2025)"},{"key":"19_CR7","doi-asserted-by":"crossref","unstructured":"Chen, L., et al.: Sharegpt4v: Improving large multi-modal models with better captions. In: European Conference on Computer Vision, pp. 370\u2013387. Springer (2024)","DOI":"10.1007\/978-3-031-72643-9_22"},{"key":"19_CR8","unstructured":"Clark, A., Donahue, J., Simonyan, K.: Adversarial video generation on complex datasets (2019). arXiv:1907.06571 arXiv preprint"},{"issue":"9","key":"19_CR9","doi-asserted-by":"publisher","first-page":"10850","DOI":"10.1109\/TPAMI.2023.3261988","volume":"45","author":"FA Croitoru","year":"2023","unstructured":"Croitoru, F.A., Hondru, V., Ionescu, R.T., Shah, M.: Diffusion models in vision: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 45(9), 10850\u201310869 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"19_CR10","unstructured":"Cui, J., et al.: Lol: Longer than longer, scaling video generation to hour. arXiv preprint arXiv:2601.16914 (2026)"},{"key":"19_CR11","unstructured":"Deng, H., et al.: Autoregressive video generation without vector quantization. In: International Conference on Learning Representations (ICLR) (2025)"},{"issue":"12","key":"19_CR12","doi-asserted-by":"publisher","first-page":"2379","DOI":"10.1364\/JOSAA.4.002379","volume":"4","author":"DJ Field","year":"1987","unstructured":"Field, D.J.: Relations between the statistics of natural images and the response properties of cortical cells. J. Opt. Soc. Am. A 4(12), 2379\u20132394 (1987)","journal-title":"J. Opt. Soc. Am. A"},{"issue":"3","key":"19_CR13","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1109\/TASSP.1974.1162572","volume":"22","author":"A Gray","year":"1974","unstructured":"Gray, A., Markel, J.: A spectral-flatness measure for studying the autocorrelation method of linear prediction of speech analysis. IEEE Trans. Acoust. Speech Signal Process. 22(3), 207\u2013217 (1974)","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"key":"19_CR14","doi-asserted-by":"crossref","unstructured":"Henschel, R., et al.: Streamingt2v: consistent, dynamic, and extendable long video generation from text. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 2568\u20132577 (2025)","DOI":"10.1109\/CVPR52734.2025.00245"},{"key":"19_CR15","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_CR16","doi-asserted-by":"publisher","first-page":"8633","DOI":"10.52202\/068431-0628","volume":"35","author":"J Ho","year":"2022","unstructured":"Ho, J., Salimans, T., Gritsenko, A., Chan, W., Norouzi, M., Fleet, D.J.: Video diffusion models. Adv. Neural. Inf. Process. Syst. 35, 8633\u20138646 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"19_CR17","unstructured":"Hu, E.J., et al.: Lora: low-rank adaptation of large language models. In: International Conference on Learning Representations (ICLR) (2022)"},{"issue":"5","key":"19_CR18","doi-asserted-by":"publisher","first-page":"1562","DOI":"10.1109\/TPAMI.2019.2957464","volume":"43","author":"L Huang","year":"2019","unstructured":"Huang, L., Zhao, X., Huang, K.: Got-10k: a large high-diversity benchmark for generic object tracking in the wild. IEEE Trans. Pattern Anal. Mach. Intell. 43(5), 1562\u20131577 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"19_CR19","doi-asserted-by":"crossref","unstructured":"Huang, X., Li, Z., He, G., Zhou, M., Shechtman, E.: Self forcing: bridging the train-test gap in autoregressive video diffusion. In: Advances in Neural Information Processing Systems (NeurIPS) (2025)","DOI":"10.52202\/085713-5576"},{"key":"19_CR20","doi-asserted-by":"crossref","unstructured":"Huang, Z., et\u00a0al.: Vbench: comprehensive benchmark suite for video generative models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21807\u201321818 (2024)","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"19_CR21","unstructured":"Jang, S., Ki, T., Jo, J., Xie, S., Yoon, J., Hwang, S.J.: Self-refining video sampling. In: International Conference on Machine Learning (ICML) (2026)"},{"key":"19_CR22","unstructured":"Jazbec, M., Wong-Toi, E., Xia, G., Zhang, D., Nalisnick, E., Mandt, S.: Generative uncertainty in diffusion models. In: Uncertainty in Artificial Intelligence (UAI) (2025)"},{"key":"19_CR23","doi-asserted-by":"publisher","first-page":"89834","DOI":"10.52202\/079017-2853","volume":"37","author":"J Kim","year":"2024","unstructured":"Kim, J., Kang, J., Choi, J., Han, B.: Fifo-diffusion: generating infinite videos from text without training. Adv. Neural. Inf. Process. Syst. 37, 89834\u201389868 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"19_CR24","unstructured":"Kim, S., Kim, M., Park, D.: Test-time alignment of diffusion models without reward over-optimization. In: International Conference on Learning Representations (ICLR) (2025)"},{"key":"19_CR25","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_CR26","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. In: International Conference on Learning Representations (ICLR) (2014)"},{"key":"19_CR27","unstructured":"Kondratyuk, D., et al.: Videopoet: a large language model for zero-shot video generation. In: International Conference on Machine Learning (ICML) (2024)"},{"key":"19_CR28","unstructured":"Kong, W., et\u00a0al.: Hunyuanvideo: A systematic framework for large video generative models. arXiv preprint arXiv:2412.03603 (2024)"},{"key":"19_CR29","unstructured":"Li, W., Pan, W., Luan, P.C., Gao, Y., Alahi, A.: Stable video infinity: infinite-length video generation with error recycling (2025). arXiv:2510.09212 arXiv preprint"},{"key":"19_CR30","unstructured":"Lipman, Y., Chen, R.T., Ben-Hamu, H., Nickel, M., Le, M.: Flow matching for generative modeling. In: International Conference on Learning Representations (ICLR) (2023)"},{"key":"19_CR31","unstructured":"Liu, K., Hu, W., Xu, J., Shan, Y., Lu, S.: Rolling forcing: autoregressive long video diffusion in real time. In: International Conference on Learning Representations (ICLR) (2026)"},{"key":"19_CR32","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (ICLR) (2019)"},{"key":"19_CR33","doi-asserted-by":"publisher","first-page":"131434","DOI":"10.52202\/079017-4177","volume":"37","author":"Y Lu","year":"2024","unstructured":"Lu, Y., Liang, Y., Zhu, L., Yang, Y.: Freelong: training-free long video generation with spectralblend temporal attention. Adv. Neural. Inf. Process. Syst. 37, 131434\u2013131455 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"19_CR34","unstructured":"Lu, Y., et\u00a0al.: Reward forcing: efficient streaming video generation with rewarded distribution matching distillation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 34385\u201334397 (2026)"},{"issue":"23","key":"19_CR35","doi-asserted-by":"publisher","first-page":"1195","DOI":"10.1049\/el.2009.1977","volume":"45","author":"N Madhu","year":"2009","unstructured":"Madhu, N.: Note on measures for spectral flatness. Electron. Lett. 45(23), 1195\u20131196 (2009)","journal-title":"Electron. Lett."},{"key":"19_CR36","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4195\u20134205 (2023)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"19_CR37","unstructured":"Qiu, H., et al.: Freenoise: tuning-free longer video diffusion via noise rescheduling (2023). arXiv:2310.15169 arXiv preprint"},{"key":"19_CR38","unstructured":"Qu, L., Wang, Z., Zheng, N., Wang, W., Nie, L., Chua, T.S.: Ttom: test-time optimization and memorization for compositional video generation. arXiv preprint arXiv:2510.07940 (2025)"},{"key":"19_CR39","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 234\u2013241. Springer (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"19_CR40","unstructured":"Singer, U., et al.: Make-a-video: text-to-video generation without text-video data. In: International Conference on Learning Representations (ICLR) (2023)"},{"key":"19_CR41","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: International Conference on Learning Representations (ICLR) (2021)"},{"key":"19_CR42","unstructured":"Song, Y., Sohl-Dickstein, J., Kingma, D.P., Kumar, A., Ermon, S., Poole, B.: Score-based generative modeling through stochastic differential equations. In: International Conference on Learning Representations (ICLR) (2021)"},{"key":"19_CR43","doi-asserted-by":"crossref","unstructured":"Sun, P., Cao, J., Jiang, Y., Yuan, Z., Bai, S., Kitani, K., Luo, P.: Dancetrack: multi-object tracking in uniform appearance and diverse motion. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 20993\u201321002 (2022)","DOI":"10.1109\/CVPR52688.2022.02032"},{"key":"19_CR44","doi-asserted-by":"crossref","unstructured":"Tulyakov, S., Liu, M.Y., Yang, X., Kautz, J.: Mocogan: decomposing motion and content for video generation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1526\u20131535 (2018)","DOI":"10.1109\/CVPR.2018.00165"},{"key":"19_CR45","unstructured":"Unterthiner, T., Van Steenkiste, S., Kurach, K., Marinier, R., Michalski, M., Gelly, S.: Fvd: a new metric for video generation. In: Deep Generative Models for Highly Structured Data, ICLR 2019 Workshop, (2019)"},{"key":"19_CR46","unstructured":"Villegas, R., et al.: Phenaki: variable length video generation from open domain textual description. In: International Conference on Learning Representations (ICLR) (2023)"},{"key":"19_CR47","unstructured":"Wan, T., et\u00a0al.: Wan: open and advanced large-scale video generative models. arXiv preprint arXiv:2503.20314 (2025)"},{"key":"19_CR48","unstructured":"Wang, F.Y., Chen, W., Song, G., Ye, H.J., Liu, Y., Li, H.: Gen-l-video: multi-text to long video generation via temporal co-denoising (2023). arXiv:2305.18264 arXiv preprint"},{"key":"19_CR49","doi-asserted-by":"publisher","first-page":"24824","DOI":"10.52202\/068431-1800","volume":"35","author":"J Wei","year":"2022","unstructured":"Wei, J., et al.: Chain-of-thought prompting elicits reasoning in large language models. Adv. Neural. Inf. Process. Syst. 35, 24824\u201324837 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"19_CR50","unstructured":"Xiang, X., et al.: Pathwise test-time correction for autoregressive long video generation. arXiv preprint arXiv:2602.05871 (2026)"},{"key":"19_CR51","doi-asserted-by":"crossref","unstructured":"Xie, D., et al.: Progressive autoregressive video diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (2025)","DOI":"10.1109\/CVPRW67362.2025.00628"},{"key":"19_CR52","doi-asserted-by":"publisher","unstructured":"Xing, Z., et al.: A survey on video diffusion models. ACM Comput. Surv. 57(2), November 2024. https:\/\/doi.org\/10.1145\/3696415, https:\/\/doi.org\/10.1145\/3696415","DOI":"10.1145\/3696415"},{"key":"19_CR53","doi-asserted-by":"crossref","unstructured":"Xu, J., Mei, T., Yao, T., Rui, Y.: Msr-vtt: A large video description dataset for bridging video and language. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5288\u20135296 (2016)","DOI":"10.1109\/CVPR.2016.571"},{"key":"19_CR54","doi-asserted-by":"crossref","unstructured":"Xue, H., et al.: Advancing high-resolution video-language representation with large-scale video transcriptions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5036\u20135045 (2022)","DOI":"10.1109\/CVPR52688.2022.00498"},{"key":"19_CR55","unstructured":"Yan, W., Zhang, Y., Abbeel, P., Srinivas, A.: Videogpt: Video generation using vq-vae and transformers (2021). arXiv:2104.10157 arXiv preprint"},{"key":"19_CR56","unstructured":"Yang, S., et al.: Longlive: real-time interactive long video generation. In: International Conference on Learning Representations (ICLR) (2026)"},{"key":"19_CR57","doi-asserted-by":"crossref","unstructured":"Yin, T., et al.: From slow bidirectional to fast autoregressive video diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22963\u201322974 (2025)","DOI":"10.1109\/CVPR52734.2025.02138"},{"key":"19_CR58","doi-asserted-by":"crossref","unstructured":"Yu, L., et al.: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10459\u201310469 (2023). Magvit: Masked generative video transformer","DOI":"10.1109\/CVPR52729.2023.01008"},{"key":"19_CR59","unstructured":"Yu, Z., et al.: Autorefiner: improving autoregressive video diffusion models via reflective refinement over the stochastic sampling path. arXiv preprint arXiv:2512.11203 (2025)"},{"key":"19_CR60","unstructured":"Zhang, Z., et al.: Blockvid: Block diffusion for high-quality and consistent minute-long video generation (2025). arXiv:2511.22973 arXiv preprint"}],"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_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T10:16:24Z","timestamp":1789035384000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37362-5_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032373618","9783032373625"],"references-count":60,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37362-5_19","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"}}]}}