{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T19:09:15Z","timestamp":1788894555676,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370341","type":"print"},{"value":"9783032370358","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\/978-3-032-37035-8_3","type":"book-chapter","created":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T18:56:11Z","timestamp":1788893771000},"page":"39-56","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["TRaM-VSR: Importance-Aware Token Routing and\u00a0Merging for\u00a0One-Step Diffusion Video Super-Resolution"],"prefix":"10.1007","author":[{"given":"Sicheng","family":"Gao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuyun","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yixuan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tong","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zongwei","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Radu","family":"Timofte","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,9]]},"reference":[{"key":"3_CR1","doi-asserted-by":"crossref","unstructured":"Blattmann, A., et al.: Align your latents: high-resolution video synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"3_CR2","unstructured":"Bolya, D., Fu, C.Y., Dai, X., Zhang, P., Feichtenhofer, C., Hoffman, J.: Token merging: your ViT but faster. In: International Conference on Learning Representations (ICLR) (2023)"},{"key":"3_CR3","doi-asserted-by":"crossref","unstructured":"Bolya, D., Hoffman, J.: Token merging for fast stable diffusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (2023)","DOI":"10.1109\/CVPRW59228.2023.00484"},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Castells, T., Song, H.K., Kim, B.K., Choi, S.: LD-Pruner: efficient pruning of latent diffusion models using task-agnostic insights. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (2024)","DOI":"10.1109\/CVPRW63382.2024.00087"},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"Chan, K.C., Zhou, S., Xu, X., Loy, C.C.: Investigating tradeoffs in real-world video super-resolution. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5962\u20135971 (2022)","DOI":"10.1109\/CVPR52688.2022.00588"},{"key":"3_CR6","doi-asserted-by":"publisher","unstructured":"Chen, Z., et al.: Dove: efficient one-step diffusion model for real-world video super-resolution (2025). https:\/\/doi.org\/10.48550\/arXiv.2505.16239","DOI":"10.48550\/arXiv.2505.16239"},{"issue":"5","key":"3_CR7","first-page":"2567","volume":"44","author":"K Ding","year":"2020","unstructured":"Ding, K., Ma, K., Wang, S., Simoncelli, E.P.: Image quality assessment: unifying structure and texture similarity. IEEE Trans. Pattern Anal. Mach. Intell. 44(5), 2567\u20132581 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3_CR8","doi-asserted-by":"publisher","first-page":"30150","DOI":"10.52202\/068431-2186","volume":"35","author":"T Dockhorn","year":"2022","unstructured":"Dockhorn, T., Vahdat, A., Kreis, K.: Genie: higher-order denoising diffusion solvers. Adv. Neural. Inf. Process. Syst. 35, 30150\u201330166 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR9","unstructured":"Dong, L., et al.: TinySR: pruning diffusion for real-world image super-resolution (2025)"},{"key":"3_CR10","doi-asserted-by":"crossref","unstructured":"Esser, P., Chiu, J., Atighehchian, P., Gritsenko, A., Fidler, S.: Structure and content-guided video synthesis with diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Fang, G., Li, K., Ma, X., Wang, X.: Tinyfusion: diffusion transformers learned shallow. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 18144\u201318154 (2025)","DOI":"10.1109\/CVPR52734.2025.01691"},{"key":"3_CR12","doi-asserted-by":"crossref","unstructured":"Fang, G., Ma, X., Wang, X.: Structural pruning for diffusion models. In: Advances in Neural Information Processing Systems (NeurIPS) (2023)","DOI":"10.52202\/075280-0731"},{"key":"3_CR13","unstructured":"He, J., et al.: VEnhancer: generative space-time enhancement for video generation. arXiv:2407.07667 (2024)"},{"key":"3_CR14","doi-asserted-by":"crossref","unstructured":"Karras, T., Aittala, M., Lehtinen, J., Hellsten, J., Aila, T., Laine, S.: Analyzing and improving the training dynamics of diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 24174\u201324184 (2024)","DOI":"10.1109\/CVPR52733.2024.02282"},{"key":"3_CR15","doi-asserted-by":"crossref","unstructured":"Ke, J., Wang, Q., Wang, Y., Milanfar, P., Yang, F.: MUSIQ: multi-scale image quality transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 5148\u20135157 (2021)","DOI":"10.1109\/ICCV48922.2021.00510"},{"key":"3_CR16","doi-asserted-by":"crossref","unstructured":"Khachatryan, L., Movsisyan, A., Tadevosyan, V., Navasardyan, R., Shi, Y., Sargsyan, S.: Text2video-zero: text-to-image diffusion models are zero-shot video generators. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"3_CR17","doi-asserted-by":"crossref","unstructured":"Lai, W.S., Huang, J.B., Wang, O., Shechtman, E., Yumer, E., Yang, M.H.: Learning blind video temporal consistency. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 170\u2013185 (2018)","DOI":"10.1007\/978-3-030-01267-0_11"},{"key":"3_CR18","unstructured":"Li, H., et al.: OS-DIFFVSR: towards one-step latent diffusion model for high-detailed real-world video super-resolution (2025)"},{"key":"3_CR19","doi-asserted-by":"crossref","unstructured":"Li, X., Ma, C., Yang, X., Yang, M.H.: VidToMe: video token merging for zero-shot video editing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.00715"},{"key":"3_CR20","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: ULTRAVSR: achieving ultra-realistic video super-resolution with efficient one-step diffusion space (2025)","DOI":"10.1145\/3746027.3755117"},{"key":"3_CR21","unstructured":"Luo, S., Chen, Y., Sun, Y., Li, L., Li, J., Zhao, H.: Latent consistency models: synthesizing high-resolution images with few-step inference (2023)"},{"key":"3_CR22","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 (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"3_CR23","unstructured":"Shen, H.: Efficient diffusion models: a survey. Trans. Mach. Learn. Res. (TMLR) (2025)"},{"key":"3_CR24","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":"3_CR25","doi-asserted-by":"crossref","unstructured":"Sun, Y., Sun, L., Liu, S., Wu, R., Zhang, Z., Zhang, L.: One-step diffusion for detail-rich and temporally consistent video super-resolution (2025)","DOI":"10.52202\/085713-5752"},{"key":"3_CR26","doi-asserted-by":"publisher","first-page":"1363","DOI":"10.52202\/075280-0068","volume":"36","author":"L Tang","year":"2023","unstructured":"Tang, L., Jia, M., Wang, Q., Phoo, C.P., Hariharan, B.: Emergent correspondence from image diffusion. Adv. Neural. Inf. Process. Syst. 36, 1363\u20131389 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR27","doi-asserted-by":"crossref","unstructured":"Tao, X., Gao, H., Liao, R., Wang, J., Jia, J.: Detail-revealing deep video super-resolution. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 4472\u20134480 (2017)","DOI":"10.1109\/ICCV.2017.479"},{"key":"3_CR28","unstructured":"Villegas, R., et al.: Phenaki: variable length video generation from open domain textual descriptions. In: International Conference on Learning Representations (ICLR) (2023)"},{"key":"3_CR29","doi-asserted-by":"crossref","unstructured":"Wang, H., et al.: Attention-driven training-free efficiency enhancement of diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.01522"},{"key":"3_CR30","doi-asserted-by":"crossref","unstructured":"Wang, J., Chan, K.C., Loy, C.C.: Exploring CLIP for assessing the look and feel of images. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, pp. 2555\u20132563 (2023)","DOI":"10.1609\/aaai.v37i2.25353"},{"key":"3_CR31","unstructured":"Wang, J., et\u00a0al.: Seedvr2: one-step video restoration via diffusion adversarial post-training. arXiv preprint arXiv:2506.05301 (2025)"},{"key":"3_CR32","doi-asserted-by":"crossref","unstructured":"Wang, J., et al.: SEEDVR: seeding infinity in diffusion transformer towards generic video restoration. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2161\u20132172 (2025)","DOI":"10.1109\/CVPR52734.2025.00207"},{"key":"3_CR33","doi-asserted-by":"crossref","unstructured":"Wang, R., et al.: Benchmark dataset and effective inter-frame alignment for real-world video super-resolution. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1168\u20131177 (2023)","DOI":"10.1109\/CVPRW59228.2023.00124"},{"key":"3_CR34","doi-asserted-by":"crossref","unstructured":"Wang, X., Xie, L., Dong, C., Shan, Y.: Real-ESRGAN: training real-world blind super-resolution with pure synthetic data. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 1905\u20131914 (2021)","DOI":"10.1109\/ICCVW54120.2021.00217"},{"key":"3_CR35","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: LAVIE: high-quality video generation with cascaded latent diffusion models. Int. J. Comput. Vision (IJCV) (2024)","DOI":"10.1007\/s11263-024-02295-1"},{"issue":"4","key":"3_CR36","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600\u2013612 (2004)","journal-title":"IEEE Trans. Image Process."},{"key":"3_CR37","doi-asserted-by":"crossref","unstructured":"Wu, R., et al.: SeeSR: towards semantics-aware real-world image super-resolution. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.02405"},{"key":"3_CR38","doi-asserted-by":"crossref","unstructured":"Xie, R., et al.: Star: spatial-temporal augmentation with text-to-video models for real-world video super-resolution. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 17108\u201317118 (2025)","DOI":"10.1109\/ICCV51701.2025.01589"},{"key":"3_CR39","doi-asserted-by":"crossref","unstructured":"Yang, X., He, C., Ma, J., Zhang, L.: Motion-guided latent diffusion for temporally consistent real-world video super-resolution. In: European Conference on Computer Vision, pp. 224\u2013242. Springer (2024)","DOI":"10.1007\/978-3-031-72784-9_13"},{"key":"3_CR40","doi-asserted-by":"crossref","unstructured":"Yang, X., Xiang, W., Zeng, H., Zhang, L.: Real-world video super-resolution: a benchmark dataset and a decomposition based learning scheme. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 4781\u20134790 (2021)","DOI":"10.1109\/ICCV48922.2021.00474"},{"key":"3_CR41","doi-asserted-by":"crossref","unstructured":"Yi, P., Wang, Z., Jiang, K., Jiang, J., Ma, J.: Progressive fusion video super-resolution network via exploiting non-local spatio-temporal correlations. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 3106\u20133115 (2019)","DOI":"10.1109\/ICCV.2019.00320"},{"issue":"1","key":"3_CR42","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1109\/TPAMI.2024.3461721","volume":"47","author":"Z Yue","year":"2025","unstructured":"Yue, Z., Wang, J., Loy, C.C.: Efficient diffusion model for image restoration by residual shifting. IEEE Trans. Pattern Anal. Mach. Intell. 47(1), 116\u2013130 (2025). https:\/\/doi.org\/10.1109\/TPAMI.2024.3461721","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3_CR43","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 586\u2013595 (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"3_CR44","doi-asserted-by":"crossref","unstructured":"Zhou, S., Wang, J., Chan, K.C., Loy, C.C.: Upscale-a-video: temporal-consistent diffusion model for real-world video super-resolution. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.00245"}],"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\/978-3-032-37035-8_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T18:56:17Z","timestamp":1788893777000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37035-8_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370341","9783032370358"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37035-8_3","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":"9 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"}}]}}