{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T08:17:00Z","timestamp":1772093820025,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":43,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819549719","type":"print"},{"value":"9789819549726","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T00:00:00Z","timestamp":1764201600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T00:00:00Z","timestamp":1764201600000},"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\/978-981-95-4972-6_9","type":"book-chapter","created":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T08:07:44Z","timestamp":1764144464000},"page":"109-120","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["NoPo3DFusion: Scaling Two Images to\u00a0Long Videos via\u00a03D-Aware Iterative Diffusion"],"prefix":"10.1007","author":[{"given":"Xiaolong","family":"Shen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Donny Y.","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tien-Tsin","family":"Wong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianfei","family":"Cai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,11,27]]},"reference":[{"key":"9_CR1","unstructured":"Blattmann, A., et\u00a0al.: Stable video diffusion: scaling latent video diffusion models to large datasets. arXiv preprint arXiv:2311.15127 (2023)"},{"key":"9_CR2","doi-asserted-by":"crossref","unstructured":"Charatan, D., Li, S.L., Tagliasacchi, A., Sitzmann, V.: Pixelsplat: 3d gaussian splats from image pairs for scalable generalizable 3d reconstruction. In: CVPR, pp. 19457\u201319467 (2024)","DOI":"10.1109\/CVPR52733.2024.01840"},{"key":"9_CR3","doi-asserted-by":"crossref","unstructured":"Chen, A., et al.: Mvsnerf: fast generalizable radiance field reconstruction from multi-view stereo. In: ICCV, pp. 14124\u201314133 (2021)","DOI":"10.1109\/ICCV48922.2021.01386"},{"key":"9_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Y., Xu, H., Wu, Q., Zheng, C., Cham, T.J., Cai, J.: Explicit correspondence matching for generalizable neural radiance fields. TPAMI (2025)","DOI":"10.1109\/TPAMI.2025.3598711"},{"key":"9_CR5","doi-asserted-by":"publisher","unstructured":"Chen, Y., et al.: MVSplat: efficient 3D gaussian splatting from sparse multi-view images. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) Computer Vision \u2013 ECCV 2024. ECCV 2024. LNCS, vol. 15079, pp. 370\u2013386. Springer, Cham (2025). https:\/\/doi.org\/10.1007\/978-3-031-72664-4_21","DOI":"10.1007\/978-3-031-72664-4_21"},{"key":"9_CR6","first-page":"107064","volume":"37","author":"Y Chen","year":"2024","unstructured":"Chen, Y., et al.: Mvsplat360: feed-forward 360 scene synthesis from sparse views. NeurIPS 37, 107064\u2013107086 (2024)","journal-title":"NeurIPS"},{"key":"9_CR7","first-page":"75468","volume":"37","author":"R Gao","year":"2024","unstructured":"Gao, R., et al.: Cat3d: create anything in 3d with multi-view diffusion models. NeurIPS 37, 75468\u201375494 (2024)","journal-title":"NeurIPS"},{"key":"9_CR8","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. NeurIPS 33, 6840\u20136851 (2020)","journal-title":"NeurIPS"},{"key":"9_CR9","doi-asserted-by":"crossref","unstructured":"Kerbl, B., Kopanas, G., Leimk\u00fchler, T., Drettakis, G.: 3D gaussian splatting for real-time radiance field rendering. ACM Trans. Graph. 42(4), 139\u20131 (2023)","DOI":"10.1145\/3592433"},{"key":"9_CR10","doi-asserted-by":"publisher","unstructured":"Leroy, V., Cabon, Y., Revaud, J.: Grounding image matching in 3D with MASt3R. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) Computer Vision \u2013 ECCV 2024. ECCV 2024. LNCS, vol. 15130, pp. 71\u201391. Springer, Cham (2025). https:\/\/doi.org\/10.1007\/978-3-031-73220-1_5","DOI":"10.1007\/978-3-031-73220-1_5"},{"key":"9_CR11","doi-asserted-by":"crossref","unstructured":"Liu, A., Tucker, R., Jampani, V., Makadia, A., Snavely, N., Kanazawa, A.: Infinite nature: perpetual view generation of natural scenes from a single image. In: ICCV, pp. 14458\u201314467 (2021)","DOI":"10.1109\/ICCV48922.2021.01419"},{"key":"9_CR12","doi-asserted-by":"crossref","unstructured":"Liu, R., Wu, R., Van\u00a0Hoorick, B., Tokmakov, P., Zakharov, S., Vondrick, C.: Zero-1-to-3: zero-shot one image to 3d object. In: ICCV, pp. 9298\u20139309 (2023)","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"9_CR13","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: ICLR (2019)"},{"key":"9_CR14","doi-asserted-by":"crossref","unstructured":"Mildenhall, B., Srinivasan, P.P., Tancik, M., Barron, J.T., Ramamoorthi, R., Ng, R.: Nerf: representing scenes as neural radiance fields for view synthesis. In: ECCV, pp. 405\u2013421 (2020)","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"9_CR15","doi-asserted-by":"crossref","unstructured":"M\u00fcller, N., et al.: Multidiff: consistent novel view synthesis from a single image. In: CVPR, pp. 10258\u201310268 (2024)","DOI":"10.1109\/CVPR52733.2024.00977"},{"key":"9_CR16","unstructured":"Nichol, A.Q., Dhariwal, P.: Improved denoising diffusion probabilistic models. In: ICML, pp. 8162\u20138171. PMLR (2021)"},{"key":"9_CR17","doi-asserted-by":"crossref","unstructured":"Sargent, K., et\u00a0al.: Zeronvs: zero-shot 360-degree view synthesis from a single image. In: CVPR, pp. 9420\u20139429 (2024)","DOI":"10.1109\/CVPR52733.2024.00900"},{"key":"9_CR18","unstructured":"Shi, D., et al.: Revisiting depth representations for feed-forward 3d gaussian splatting. arXiv preprint arXiv:2506.05327 (2025)"},{"key":"9_CR19","unstructured":"Smart, B., Zheng, C., Laina, I., Prisacariu, V.A.: Splatt3r: zero-shot gaussian splatting from uncalibrated image pairs. arXiv preprint arXiv:2408.13912 (2024)"},{"key":"9_CR20","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: ICML, pp. 2256\u20132265. pmlr (2015)"},{"key":"9_CR21","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: ICLR (2021)"},{"key":"9_CR22","doi-asserted-by":"crossref","unstructured":"Song, Y., Ermon, S.: Generative modeling by estimating gradients of the data distribution. NeurIPS 32 (2019)","DOI":"10.1609\/aaai.v32i1.11827"},{"key":"9_CR23","doi-asserted-by":"crossref","unstructured":"Szymanowicz, S., et al.: Flash3d: feed-forward generalisable 3d scene reconstruction from a single image. In: 3DV (2025)","DOI":"10.1109\/3DV66043.2025.00067"},{"key":"9_CR24","doi-asserted-by":"crossref","unstructured":"Szymanowicz, S., Rupprecht, C., Vedaldi, A.: Splatter image: ultra-fast single-view 3d reconstruction. In: CVPR, pp. 10208\u201310217 (2024)","DOI":"10.1109\/CVPR52733.2024.00972"},{"key":"9_CR25","doi-asserted-by":"publisher","unstructured":"Voleti, V., et al.: SV3D: novel multi-view synthesis and 3d generation from a single image using latent video diffusion. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) Computer Vision \u2013 ECCV 2024. ECCV 2024. LNCS, vol. 15059, pp. 439\u2013457. Springer, Cham (2025). https:\/\/doi.org\/10.1007\/978-3-031-73232-4_25","DOI":"10.1007\/978-3-031-73232-4_25"},{"key":"9_CR26","doi-asserted-by":"crossref","unstructured":"Wang, Q., et al.: Ibrnet: learning multi-view image-based rendering. In: CVPR, pp. 4690\u20134699 (2021)","DOI":"10.1109\/CVPR46437.2021.00466"},{"key":"9_CR27","doi-asserted-by":"crossref","unstructured":"Wang, S., Leroy, V., Cabon, Y., Chidlovskii, B., Revaud, J.: Dust3r: geometric 3d vision made easy. In: CVPR, pp. 20697\u201320709 (2024)","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"9_CR28","unstructured":"Wang, W., Chen, D.Y., Zhang, Z., Shi, D., Liu, A., Zhuang, B.: Zpressor: bottleneck-aware compression for scalable feed-forward 3dgs. In: NeurIPS (2025)"},{"key":"9_CR29","unstructured":"Wang, W., et al.: Volsplat: rethinking feed-forward 3d gaussian splatting with voxel-aligned prediction. arXiv preprint arXiv:2509.19297 (2025)"},{"key":"9_CR30","first-page":"107326","volume":"37","author":"Y Wang","year":"2024","unstructured":"Wang, Y., Huang, T., Chen, H., Lee, G.H.: Freesplat: generalizable 3d gaussian splatting towards free view synthesis of indoor scenes. NeurIPS 37, 107326\u2013107349 (2024)","journal-title":"NeurIPS"},{"issue":"4","key":"9_CR31","first-page":"600","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. TIP 13(4), 600\u2013612 (2004)","journal-title":"TIP"},{"key":"9_CR32","unstructured":"Watson, D., Chan, W., Martin-Brualla, R., Ho, J., Tagliasacchi, A., Norouzi, M.: Novel view synthesis with diffusion models. In: ICLR (2023)"},{"key":"9_CR33","doi-asserted-by":"publisher","unstructured":"Wewer, C., Raj, K., Ilg, E., Schiele, B., Lenssen, J.E.: LatentSplat: autoencoding variational gaussians for fast generalizable 3D reconstruction. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) Computer Vision \u2013 ECCV 2024. ECCV 2024. LNCS, vol. 15145, pp. 456\u2013473. Springer, Cham (2025). https:\/\/doi.org\/10.1007\/978-3-031-73021-4_27","DOI":"10.1007\/978-3-031-73021-4_27"},{"key":"9_CR34","doi-asserted-by":"crossref","unstructured":"Xu, H., et al.: Murf: multi-baseline radiance fields. In: CVPR, pp. 20041\u201320050 (2024)","DOI":"10.1109\/CVPR52733.2024.01894"},{"key":"9_CR35","doi-asserted-by":"crossref","unstructured":"Xu, H., et al.: Depthsplat: connecting gaussian splatting and depth. In: CVPR, pp. 16453\u201316463 (2025)","DOI":"10.1109\/CVPR52734.2025.01534"},{"key":"9_CR36","unstructured":"Yang, Z., et\u00a0al.: Cogvideox: text-to-video diffusion models with an expert transformer. In: ICLR (2025)"},{"key":"9_CR37","unstructured":"Ye, B., et al.: No pose, no problem: surprisingly simple 3d gaussian splats from sparse unposed images. In: ICLR (2025)"},{"key":"9_CR38","doi-asserted-by":"crossref","unstructured":"Ye, J., Wang, P., Li, K., Shi, Y., Wang, H.: Consistent-1-to-3: consistent image to 3d view synthesis via geometry-aware diffusion models. In: 3DV, pp. 664\u2013674. IEEE (2024)","DOI":"10.1109\/3DV62453.2024.00027"},{"key":"9_CR39","doi-asserted-by":"crossref","unstructured":"Yu, A., Ye, V., Tancik, M., Kanazawa, A.: Pixelnerf: neural radiance fields from one or few images. In: CVPR, pp. 4578\u20134587 (2021)","DOI":"10.1109\/CVPR46437.2021.00455"},{"key":"9_CR40","doi-asserted-by":"crossref","unstructured":"Yu, W., et al.: Viewcrafter: taming video diffusion models for high-fidelity novel view synthesis. arXiv preprint arXiv:2409.02048 (2024)","DOI":"10.1109\/TPAMI.2025.3613256"},{"key":"9_CR41","doi-asserted-by":"crossref","unstructured":"Zhang, C., Xu, H., Wu, Q., Gambardella, C.C., Phung, D., Cai, J.: Pansplat: 4k panorama synthesis with feed-forward gaussian splatting. In: CVPR, pp. 11437\u201311447 (2025)","DOI":"10.1109\/CVPR52734.2025.01068"},{"key":"9_CR42","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: CVPR, pp. 586\u2013595 (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"9_CR43","doi-asserted-by":"crossref","unstructured":"Zhou, T., Tucker, R., Flynn, J., Fyffe, G., Snavely, N.: Stereo magnification: learning view synthesis using multiplane images. ACM Trans. Graph (2018)","DOI":"10.1145\/3197517.3201323"}],"container-title":["Lecture Notes in Computer Science","AI 2025: Advances in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-4972-6_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T07:23:57Z","timestamp":1772090637000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-4972-6_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,27]]},"ISBN":["9789819549719","9789819549726"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-4972-6_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,27]]},"assertion":[{"value":"27 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"AI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australasian Joint Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canberra, ACT","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 December 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"38","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ausai2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ajcai2025.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}