{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T11:10:16Z","timestamp":1789038616940,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":101,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032374639","type":"print"},{"value":"9783032374646","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\/978-3-032-37464-6_17","type":"book-chapter","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T10:29:48Z","timestamp":1789036188000},"page":"304-325","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ReconSplat: Generalizable 3D Scene Reconstruction Beyond Observed Views"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-5086-4856","authenticated-orcid":false,"given":"Giuseppe","family":"Stracquadanio","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3271-5990","authenticated-orcid":false,"given":"Kevin","family":"Raj","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8371-1734","authenticated-orcid":false,"given":"Julia","family":"Grabinski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9002-9832","authenticated-orcid":false,"given":"Stefan","family":"Roth","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,11]]},"reference":[{"key":"17_CR1","doi-asserted-by":"publisher","unstructured":"Asim, M., Wewer, C., Wimmer, T., Schiele, B., Lenssen, J.E.: MEt3R: Measuring multi-view consistency in generated images. In: CVPR, pp. 6034\u20136044 (2025). https:\/\/doi.org\/10.1109\/CVPR52734.2025.00566","DOI":"10.1109\/CVPR52734.2025.00566"},{"key":"17_CR2","unstructured":"Bahmani, S., et al.: Lyra: Generative 3D scene reconstruction via video diffusion model self-distillation. In: ICLR (2026)"},{"key":"17_CR3","doi-asserted-by":"publisher","unstructured":"Bahmani, S., et al.: AC3D: Analyzing and improving 3D camera control in video diffusion transformers. In: CVPR, pp. 22875\u201322889 (2025). https:\/\/doi.org\/10.1109\/CVPR52734.2025.02130","DOI":"10.1109\/CVPR52734.2025.02130"},{"key":"17_CR4","unstructured":"Bahmani, S., et al.: VD3D: Taming large video diffusion transformers for 3D camera control. ICLR (2025)"},{"key":"17_CR5","doi-asserted-by":"publisher","unstructured":"Barron, J.T.: A general and adaptive robust loss function. In: CVPR, pp. 4331\u20134339 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00446","DOI":"10.1109\/CVPR.2019.00446"},{"key":"17_CR6","doi-asserted-by":"publisher","unstructured":"Barron, J.T., Mildenhall, B., Verbin, D., Srinivasan, P.P., Hedman, P.: Mip-NeRF 360: Unbounded anti-aliased neural radiance fields. In: CVPR, pp. 5470\u20135479 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.00539","DOI":"10.1109\/CVPR52688.2022.00539"},{"key":"17_CR7","doi-asserted-by":"publisher","unstructured":"Barron, J.T., Mildenhall, B., Verbin, D., Srinivasan, P.P., Hedman, P.: Zip-NeRF: Anti-aliased grid-based neural radiance fields. In: CVPR, pp. 19697\u201319705 (2023). https:\/\/doi.org\/10.1109\/ICCV51070.2023.01804","DOI":"10.1109\/ICCV51070.2023.01804"},{"key":"17_CR8","doi-asserted-by":"publisher","unstructured":"Blattmann, A., et al.: Stable Video Diffusion: Scaling latent video diffusion models to large datasets. arXiv:2311.15127 [cs.CV] (2023). https:\/\/doi.org\/10.48550\/arXiv.2311.15127","DOI":"10.48550\/arXiv.2311.15127"},{"key":"17_CR9","doi-asserted-by":"publisher","unstructured":"Blattmann, A., et al.: Align your latents: High-resolution video synthesis with latent diffusion models. In: CVPR, pp. 22563\u201322575 (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.02161","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"17_CR10","doi-asserted-by":"publisher","unstructured":"Cai, Y., et\u00a0al.: Baking Gaussian splatting into diffusion denoiser for fast and scalable single-stage image-to-3D generation and reconstruction. In: ICCV, pp. 25062\u201325072 (2025). https:\/\/doi.org\/10.1109\/ICCV51701.2025.02324","DOI":"10.1109\/ICCV51701.2025.02324"},{"key":"17_CR11","doi-asserted-by":"publisher","unstructured":"Chan, E.R., et al.: Generative novel view synthesis with 3D-aware diffusion models. In: ICCV, pp. 4217\u20134229 (2023). https:\/\/doi.org\/10.1109\/ICCV51070.2023.00389","DOI":"10.1109\/ICCV51070.2023.00389"},{"key":"17_CR12","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.1109\/CVPR52733.2024.01840","DOI":"10.1109\/CVPR52733.2024.01840"},{"key":"17_CR13","doi-asserted-by":"publisher","unstructured":"Chen, S., Sun, P., Song, Y., Luo, P.: DiffusionDet: Diffusion model for object detection. In: ICCV, pp. 19830\u201319843 (2023). https:\/\/doi.org\/10.1109\/ICCV51070.2023.01816","DOI":"10.1109\/ICCV51070.2023.01816"},{"key":"17_CR14","doi-asserted-by":"publisher","unstructured":"Chen, S., et al.: Video depth anything: Consistent depth estimation for super-long videos. In: CVPR, pp. 22831\u201322840 (2025). https:\/\/doi.org\/10.1109\/CVPR52734.2025.02126","DOI":"10.1109\/CVPR52734.2025.02126"},{"key":"17_CR15","doi-asserted-by":"publisher","unstructured":"Chen, Y.,et al.: MVSplat: Efficient 3D Gaussian splatting from sparse multi-view images. In: ECCV, vol. 15079, pp. 370\u2013386 (2024). https:\/\/doi.org\/10.1007\/978-3-031-72664-4_21","DOI":"10.1007\/978-3-031-72664-4_21"},{"key":"17_CR16","doi-asserted-by":"publisher","unstructured":"Chen, Y., et al.: MVSplat360: Feed-forward 360 scene synthesis from sparse views. NeurIPS 107064\u2013107086 (2024). https:\/\/doi.org\/10.52202\/079017-3399","DOI":"10.52202\/079017-3399"},{"key":"17_CR17","doi-asserted-by":"publisher","unstructured":"Chen, Z., Qin, M., Yuan, T., Liu, Z., Zhao, H.: LONG3R: Long sequence streaming 3D reconstruction. In: ICCV, pp. 5273\u20135284 (2025). https:\/\/doi.org\/10.1109\/ICCV51701.2025.00501","DOI":"10.1109\/ICCV51701.2025.00501"},{"key":"17_CR18","doi-asserted-by":"publisher","unstructured":"Chibane, J., Bansal, A., Lazova, V., Pons-Moll, G.: Stereo Radiance Fields (SRF): Learning view synthesis for sparse views of novel scenes. In: CVPR, pp. 7911\u20137920 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.00782","DOI":"10.1109\/CVPR46437.2021.00782"},{"key":"17_CR19","doi-asserted-by":"publisher","unstructured":"Chung, J., Oh, J., Lee, K.M.: Depth-regularized optimization for 3D Gaussian splatting in few-shot images. In: CVPR, pp. 811\u2013820 (2024). https:\/\/doi.org\/10.1109\/CVPRW63382.2024.00086","DOI":"10.1109\/CVPRW63382.2024.00086"},{"key":"17_CR20","doi-asserted-by":"publisher","unstructured":"Deng, K., Liu, A., Zhu, J.Y., Ramanan, D.: Depth-supervised NeRF: Fewer views and faster training for free. In: CVPR, pp. 12882\u201312891 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01254","DOI":"10.1109\/CVPR52688.2022.01254"},{"issue":"5","key":"17_CR21","doi-asserted-by":"publisher","first-page":"2567","DOI":"10.1109\/TPAMI.2020.3045810","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). https:\/\/doi.org\/10.1109\/TPAMI.2020.3045810","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"17_CR22","doi-asserted-by":"publisher","unstructured":"Esser, P., Rombach, R., Ommer, B.: Taming transformers for high-resolution image synthesis. In: CVPR, pp. 12873\u201312883 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.01268","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"17_CR23","doi-asserted-by":"publisher","unstructured":"Gao, R., et al.: CAT3D: Create anything in 3D with multi-view diffusion models. NeurIPS 75468\u201375494 (2024). https:\/\/doi.org\/10.52202\/079017-2403","DOI":"10.52202\/079017-2403"},{"key":"17_CR24","doi-asserted-by":"crossref","unstructured":"Goodfellow, I.J., et al.: Generative adversarial nets. NeurIPS 139\u2013144 (2014)","DOI":"10.1145\/3422622"},{"key":"17_CR25","doi-asserted-by":"publisher","unstructured":"Guizilini, V., Irshad, M.Z., Chen, D., Shakhnarovich, G., Ambrus, R.: Zero-shot novel view and depth synthesis with multi-view geometric diffusion. In: CVPR, pp. 764\u2013776 (2025). https:\/\/doi.org\/10.1109\/CVPR52734.2025.00080","DOI":"10.1109\/CVPR52734.2025.00080"},{"key":"17_CR26","doi-asserted-by":"publisher","unstructured":"Hamdi, A., Ghanem, B., Nie\u00dfsner, M.: SPARF: Large-scale learning of 3D sparse radiance fields from few input images. In: ICCV Workshops, pp. 2930\u20132940 (2023). https:\/\/doi.org\/10.1109\/ICCVW60793.2023.00315","DOI":"10.1109\/ICCVW60793.2023.00315"},{"key":"17_CR27","doi-asserted-by":"publisher","unstructured":"He, Y., Yan, R., Fragkiadaki, K., Yu, S.I.: Epipolar transformers. In: CVPR, pp. 7779\u20137788 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00780","DOI":"10.1109\/CVPR42600.2020.00780"},{"key":"17_CR28","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. NeurIPS 6629\u20136640 (2017)"},{"key":"17_CR29","doi-asserted-by":"publisher","unstructured":"Ho, J., et al.: Imagen Video: High definition video generation with diffusion models. arXiv:2210.02303 [cs.CV] (2022). https:\/\/doi.org\/10.48550\/arXiv.2210.02303","DOI":"10.48550\/arXiv.2210.02303"},{"key":"17_CR30","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. NeurIPS 6840\u20136851 (2020)"},{"key":"17_CR31","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. In: NeurIPS Workshops (2021)"},{"key":"17_CR32","unstructured":"Hong, Y., et al.: LRM: Large reconstruction model for single image to 3D. In: ICLR (2024)"},{"key":"17_CR33","unstructured":"Hu, E.J., et al.: LoRA: Low-rank adaptation of large language models. In: ICLR (2022)"},{"key":"17_CR34","doi-asserted-by":"publisher","unstructured":"Hu, H., Zhou, Z., Jampani, V., Tulsiani, S.: MVD-Fusion: Single-view 3D via depth-consistent multi-view generation. In: CVPR, pp. 9698\u20139707 (2024). https:\/\/doi.org\/10.1109\/CVPR52733.2024.00926","DOI":"10.1109\/CVPR52733.2024.00926"},{"key":"17_CR35","doi-asserted-by":"publisher","unstructured":"Huang, P.H., Matzen, K., Kopf, J., Ahuja, N., Huang, J.B.: DeepMVS: Learning multi-view stereopsis. In: CVPR, pp. 2821\u20132830 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00298","DOI":"10.1109\/CVPR.2018.00298"},{"key":"17_CR36","doi-asserted-by":"publisher","unstructured":"Jevti\u0107, A., Reich, C., Wimbauer, F., Hahn, O., Rupprecht, C., Roth, S., Cremers, D.: Feed-forward SceneDINO for unsupervised semantic scene completion. In: ICCV, pp. 6784\u20136796 (2025). https:\/\/doi.org\/10.1109\/ICCV51701.2025.00638","DOI":"10.1109\/ICCV51701.2025.00638"},{"issue":"6","key":"17_CR37","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3763326","volume":"44","author":"L Jiang","year":"2025","unstructured":"Jiang, L., et al.: AnySplat: Feed-forward 3D Gaussian splatting from unconstrained views. ACM Trans. Graph. 44(6), 1\u201316 (2025). https:\/\/doi.org\/10.1145\/3763326","journal-title":"ACM Trans. Graph."},{"key":"17_CR38","unstructured":"Kang, G., et al.: iLRM: An iterative large 3D reconstruction model. In: CVPR, pp. 37332\u201337342 (2026)"},{"key":"17_CR39","unstructured":"Kang, G., Yang, S., Nam, S., Lee, Y., Kim, J., Park, E.: Multi-view Pyramid Transformer: Look coarser to see broader. In: CVPR, pp. 37380\u201337390 (2026)"},{"key":"17_CR40","doi-asserted-by":"publisher","unstructured":"Kato, H., et al.: Differentiable rendering: A survey. arXiv:2006.12057 [cs.CV] (2020). https:\/\/doi.org\/10.48550\/arXiv.2006.12057","DOI":"10.48550\/arXiv.2006.12057"},{"key":"17_CR41","doi-asserted-by":"publisher","unstructured":"Ke, B., Obukhov, A., Huang, S., Metzger, N., Daudt, R.C., Schindler, K.: Repurposing diffusion-based image generators for monocular depth estimation. In: CVPR, pp. 9492\u20139502 (2024). https:\/\/doi.org\/10.1109\/CVPR52733.2024.00907","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"17_CR42","doi-asserted-by":"publisher","unstructured":"Kerbl, B., Kopanas, G., Leimkuehler, T., Drettakis, G.: 3D Gaussian splatting for real-time radiance field rendering. ACM Trans. Graph. 42(4) (2023). https:\/\/doi.org\/10.1145\/3592433","DOI":"10.1145\/3592433"},{"key":"17_CR43","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational Bayes. ICLR (2014)"},{"key":"17_CR44","doi-asserted-by":"publisher","unstructured":"Leroy, V., Cabon, Y., Revaud, J.: Grounding image matching in 3D with MAST3R. In: ECCV, vol. 15130, pp. 71\u201391 (2024). https:\/\/doi.org\/10.1007\/978-3-031-73220-1_5","DOI":"10.1007\/978-3-031-73220-1_5"},{"key":"17_CR45","unstructured":"Li, J., et al.: Instant3D: Fast text-to-3D with sparse-view generation and large reconstruction model. In: ICLR (2024)"},{"key":"17_CR46","doi-asserted-by":"crossref","unstructured":"Li, R., Yi, B., Liu, J., Gao, H., Ma, Y., Kanazawa, A.: Cameras as relative positional encoding. In: NeurIPS, vol.\u00a038, pp. 15984\u201316009 (2025)","DOI":"10.52202\/085713-0540"},{"key":"17_CR47","doi-asserted-by":"publisher","unstructured":"Liang, H., et al.: Wonderland: Navigating 3D scenes from a single image. In: CVPR, pp. 798\u2013810 (2025). https:\/\/doi.org\/10.1109\/CVPR52734.2025.00083","DOI":"10.1109\/CVPR52734.2025.00083"},{"key":"17_CR48","unstructured":"Lin, C., Pan, P., Yang, B., Li, Z., MU, Y.: DiffSplat: Repurposing image diffusion models for scalable Gaussian splat generation. In: ICLR (2025)"},{"key":"17_CR49","doi-asserted-by":"publisher","unstructured":"Ling, L., et al.: DL3DV-10K: A large-scale scene dataset for deep learning-based 3D vision. In: CVPR, pp. 22160\u201322169 (2024). https:\/\/doi.org\/10.1109\/CVPR52733.2024.02092","DOI":"10.1109\/CVPR52733.2024.02092"},{"key":"17_CR50","doi-asserted-by":"publisher","unstructured":"Lombardi, S., Simon, T., Saragih, J., Schwartz, G., Lehrmann, A., Sheikh, Y.: Neural Volumes: Learning dynamic renderable volumes from images. ACM Trans. Graph. 38, 65:1\u201365:14 (2019). https:\/\/doi.org\/10.1145\/3306346.3323020","DOI":"10.1145\/3306346.3323020"},{"key":"17_CR51","doi-asserted-by":"publisher","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., vol. 12346, pp. 405\u2013421 (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_24","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"17_CR52","doi-asserted-by":"publisher","unstructured":"Niemeyer, M., Barron, J.T., Mildenhall, B., Sajjadi, M.S., Geiger, A., Radwan, N.: RegNeRF: Regularizing neural radiance fields for view synthesis from sparse inputs. In: CVPR, pp. 5480\u20135490 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.00540","DOI":"10.1109\/CVPR52688.2022.00540"},{"key":"17_CR53","doi-asserted-by":"publisher","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. In: ICCV, pp. 4195\u20134205 (2023). https:\/\/doi.org\/10.1109\/ICCV51070.2023.00387","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"17_CR54","unstructured":"Poole, B., Jain, A., Barron, J.T., Mildenhall, B.: DreamFusion: Text-to-3D using 2D diffusion. ICLR (2023)"},{"key":"17_CR55","doi-asserted-by":"publisher","unstructured":"Raj, K., Wewer, C., Yunus, R., Ilg, E., Lenssen, J.E.: Spurfies: Sparse-view surface reconstruction using local geometry priors. In: 3DV (2025). https:\/\/doi.org\/10.1109\/3DV66043.2025.00012","DOI":"10.1109\/3DV66043.2025.00012"},{"key":"17_CR56","doi-asserted-by":"publisher","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with CLIP latents. arXiv:2204.06125 [cs.CV] (2022). https:\/\/doi.org\/10.48550\/arXiv.2204.06125","DOI":"10.48550\/arXiv.2204.06125"},{"issue":"3","key":"17_CR57","doi-asserted-by":"publisher","first-page":"1623","DOI":"10.1109\/TPAMI.2020.3019967","volume":"44","author":"R Ranftl","year":"2020","unstructured":"Ranftl, R., Lasinger, K., Hafner, D., Schindler, K., Koltun, V.: Towards robust monocular depth estimation: Mixing datasets for zero-shot cross-dataset transfer. IEEE Trans. Pattern Anal. Mach. Intell. 44(3), 1623\u20131637 (2020). https:\/\/doi.org\/10.1109\/TPAMI.2020.3019967","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"17_CR58","doi-asserted-by":"publisher","unstructured":"Reizenstein, J., Shapovalov, R., Henzler, P., Sbordone, L., Labatut, P., Novotny, D.: Common Objects in 3D: Large-scale learning and evaluation of real-life 3D category reconstruction. In: ICCV, pp. 10901\u201310911 (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.01072","DOI":"10.1109\/ICCV48922.2021.01072"},{"key":"17_CR59","doi-asserted-by":"publisher","unstructured":"Roessle, B., Barron, J.T., Mildenhall, B., Srinivasan, P.P., Nie\u00dfner, M.: Dense depth priors for neural radiance fields from sparse input views. In: CVPR, pp. 12892\u201312901 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01255","DOI":"10.1109\/CVPR52688.2022.01255"},{"key":"17_CR60","doi-asserted-by":"publisher","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR, pp. 10684\u201310695 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01042","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"17_CR61","doi-asserted-by":"publisher","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: Convolutional networks for biomedical image segmentation. In: MICCAI, vol.\u00a09351, pp. 234\u2013241 (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"17_CR62","doi-asserted-by":"publisher","unstructured":"Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., Aberman, K.: Dreambooth: Fine tuning text-to-image diffusion models for subject-driven generation. In: CVPR, pp. 22500\u201322510 (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.02155","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"17_CR63","doi-asserted-by":"crossref","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. NeurIPS 36479\u201336494 (2022)","DOI":"10.52202\/068431-2643"},{"key":"17_CR64","unstructured":"Salimans, T., Ho, J.: Progressive distillation for fast sampling of diffusion model. ICLR (2022)"},{"key":"17_CR65","doi-asserted-by":"publisher","unstructured":"Schwarz, K., Mueller, N., Kontschieder, P.: Generative Gaussian Splatting: Generating 3D scenes with video diffusion priors. In: ICCV, pp. 27510\u201327520 (2025). https:\/\/doi.org\/10.1109\/ICCV51701.2025.02554","DOI":"10.1109\/ICCV51701.2025.02554"},{"key":"17_CR66","unstructured":"Shi, Y., Wang, P., Ye, J., Mai, L., Li, K., Yang, X.: MVDream: Multi-view diffusion for 3D generation. ICLR (2024)"},{"key":"17_CR67","unstructured":"Sitzmann, V., Zollh\u00f6fer, M., Wetzstein, G.: Scene representation networks: Continuous 3D-structure-aware neural scene representations. In: NeurIPS, pp. 1119\u20131130 (2019)"},{"key":"17_CR68","doi-asserted-by":"publisher","unstructured":"Sun, D., Roth, S., Black, M.J.: Secrets of optical flow estimation and their principles. In: CVPR, pp. 2432\u20132439 (2010). https:\/\/doi.org\/10.1109\/CVPR.2010.5539939","DOI":"10.1109\/CVPR.2010.5539939"},{"key":"17_CR69","doi-asserted-by":"publisher","unstructured":"Szymanowicz, S., et al.: Flash3D: Feed-forward generalisable 3D scene reconstruction from a single image. In: 3DV, pp. 670\u2013681 (2025). https:\/\/doi.org\/10.1109\/3DV66043.2025.00067","DOI":"10.1109\/3DV66043.2025.00067"},{"key":"17_CR70","doi-asserted-by":"publisher","unstructured":"Szymanowicz, S., Rupprecht, C., Vedaldi, A.: Splatter image: Ultra-fast single-view 3D reconstruction. In: CVPR, pp. 10208\u201310217 (2024). https:\/\/doi.org\/10.1109\/CVPR52733.2024.00972","DOI":"10.1109\/CVPR52733.2024.00972"},{"key":"17_CR71","doi-asserted-by":"publisher","unstructured":"Szymanowicz, S., et al.: Bolt3d: Generating 3D scenes in seconds. In: ICCV, pp. 24846\u201324857 (2025). https:\/\/doi.org\/10.1109\/ICCV51701.2025.02304","DOI":"10.1109\/ICCV51701.2025.02304"},{"key":"17_CR72","doi-asserted-by":"publisher","unstructured":"Tian, J., Aggarwal, L., Colaco, A., Kira, Z., Gonzalez-Franco, M.: Diffuse attend and segment: Unsupervised zero-shot segmentation using stable diffusion. In: CVPR, pp. 3554\u20133563 (2024). https:\/\/doi.org\/10.1109\/CVPR52733.2024.00341","DOI":"10.1109\/CVPR52733.2024.00341"},{"key":"17_CR73","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: ECCV, vol. 15059, pp. 439\u2013457 (2024). https:\/\/doi.org\/10.1007\/978-3-031-73232-4_25","DOI":"10.1007\/978-3-031-73232-4_25"},{"key":"17_CR74","doi-asserted-by":"publisher","unstructured":"Wang, G., Chen, Z., Loy, C.C., Liu, Z.: SparseNeRF: Distilling depth ranking for few-shot novel view synthesis. In: ICCV, pp. 9065\u20139076 (2023). https:\/\/doi.org\/10.1109\/ICCV51070.2023.00832","DOI":"10.1109\/ICCV51070.2023.00832"},{"key":"17_CR75","doi-asserted-by":"publisher","unstructured":"Wang, H., Agapito, L.: 3D reconstruction with spatial memory. In: 3DV, pp. 78\u201389 (2025). https:\/\/doi.org\/10.1109\/3DV66043.2025.00013","DOI":"10.1109\/3DV66043.2025.00013"},{"key":"17_CR76","unstructured":"Wang, H., Agapito, L.: Amb3r: Accurate feed-forward metric-scale 3D reconstruction with backend. In: CVPR (2026)"},{"key":"17_CR77","doi-asserted-by":"publisher","unstructured":"Wang, J., Chen, M., Karaev, N., Vedaldi, A., Rupprecht, C., Novotny, D.: VGGT: Visual geometry grounded transformer. In: CVPR, pp. 5294\u20135306 (2025). https:\/\/doi.org\/10.1109\/CVPR52734.2025.00499","DOI":"10.1109\/CVPR52734.2025.00499"},{"key":"17_CR78","doi-asserted-by":"publisher","unstructured":"Wang, Q., et al.: IBRNet: Learning multi-view image-based rendering. In: CVPR, pp. 4690\u20134699 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.00466","DOI":"10.1109\/CVPR46437.2021.00466"},{"key":"17_CR79","doi-asserted-by":"publisher","unstructured":"Wang, Q., Zhang, Y., Holynski, A., Efros, A.A., Kanazawa, A.: Continuous 3D perception model with persistent state. In: CVPR, pp. 10510\u201310522 (2025). https:\/\/doi.org\/10.1109\/CVPR52734.2025.00983","DOI":"10.1109\/CVPR52734.2025.00983"},{"key":"17_CR80","doi-asserted-by":"publisher","unstructured":"Wang, S., Leroy, V., Cabon, Y., Chidlovskii, B., Revaud, J.: Dust3r: Geometric 3D vision made easy. In: CVPR, pp. 20697\u201320709 (2024). https:\/\/doi.org\/10.1109\/CVPR52733.2024.01956","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"17_CR81","doi-asserted-by":"publisher","unstructured":"Wang, Y., Huang, T., Chen, H., Lee, G.H.: FreeSplat: Generalizable 3D Gaussian splatting towards free view synthesis of indoor scenes. NeurIPS 107326\u2013107349 (2024). https:\/\/doi.org\/10.52202\/079017-3409","DOI":"10.52202\/079017-3409"},{"issue":"4","key":"17_CR82","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). https:\/\/doi.org\/10.1109\/TIP.2003.819861","journal-title":"IEEE Trans. Image Process."},{"key":"17_CR83","doi-asserted-by":"publisher","unstructured":"Wang, Z., et al.: MotionCtrl: A unified and flexible motion controller for video generation. In: SIGGRAPH, pp. 1\u201311 (2024). https:\/\/doi.org\/10.1145\/3641519.3657518","DOI":"10.1145\/3641519.3657518"},{"key":"17_CR84","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: ECCV, vol. 15145, pp. 456\u2013473 (2024). https:\/\/doi.org\/10.1007\/978-3-031-73021-4_27","DOI":"10.1007\/978-3-031-73021-4_27"},{"key":"17_CR85","doi-asserted-by":"crossref","unstructured":"Wu, R., et\u00a0al.: ReconFusion: 3D reconstruction with diffusion priors. In: CVPR, pp. 21551\u201321561 (2024), https:\/\/doi.org\/10.1109\/CVPR52733.2024.02036","DOI":"10.1109\/CVPR52733.2024.02036"},{"key":"17_CR86","doi-asserted-by":"publisher","unstructured":"Xu, H., et al.: DepthSplat: Connecting Gaussian splatting and depth. In: CVPR, pp. 16453\u201316463 (2025). https:\/\/doi.org\/10.1109\/CVPR52734.2025.01534","DOI":"10.1109\/CVPR52734.2025.01534"},{"key":"17_CR87","doi-asserted-by":"publisher","unstructured":"Yang, J., et al.: Fast3R: Towards 3D reconstruction of 1000+ images in one forward pass. In: CVPR, pp. 21924\u201321935 (2025). https:\/\/doi.org\/10.1109\/CVPR52734.2025.02042","DOI":"10.1109\/CVPR52734.2025.02042"},{"key":"17_CR88","doi-asserted-by":"publisher","unstructured":"Yang, L., et al.: Depth Anything v2. In: NeurIPS, pp. 21875\u201321911 (2024). https:\/\/doi.org\/10.52202\/079017-0688","DOI":"10.52202\/079017-0688"},{"key":"17_CR89","doi-asserted-by":"publisher","unstructured":"Yang, Y., Shao, J., Li, X., Shen, Y., Geiger, A., Liao, Y.: Prometheus: 3D-aware latent diffusion models for feed-forward text-to-3D scene generation. In: CVPR, pp. 2857\u20132869 (2025). https:\/\/doi.org\/10.1109\/CVPR52734.2025.00272","DOI":"10.1109\/CVPR52734.2025.00272"},{"key":"17_CR90","doi-asserted-by":"publisher","unstructured":"Yeshwanth, C., Liu, Y.C., Nie\u00dfner, M., Dai, A.: ScanNet++: A high-fidelity dataset of 3D indoor scenes. In: ICCV, pp. 12\u201322 (2023). https:\/\/doi.org\/10.1109\/ICCV51070.2023.00008","DOI":"10.1109\/ICCV51070.2023.00008"},{"key":"17_CR91","doi-asserted-by":"publisher","unstructured":"Yu, A., Ye, V., Tancik, M., Kanazawa, A.: pixelNeRF: Neural radiance fields from one or few images. In: CVPR, pp. 4578\u20134587 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.00455","DOI":"10.1109\/CVPR46437.2021.00455"},{"key":"17_CR92","doi-asserted-by":"publisher","unstructured":"Yu, W., et al.: ViewCrafter: Taming video diffusion models for high-fidelity novel view synthesis. IEEE Trans. Pattern Anal. Mach. Intell. 1\u201318 (2025). https:\/\/doi.org\/10.1109\/TPAMI.2025.3613256","DOI":"10.1109\/TPAMI.2025.3613256"},{"key":"17_CR93","doi-asserted-by":"crossref","unstructured":"Yu, Z., Peng, S., Niemeyer, M., Sattler, T., Geiger, A.: MonoSDF: Exploring monocular geometric cues for neural implicit surface reconstruction. NeurIPS 25018\u201325032 (2022)","DOI":"10.52202\/068431-1814"},{"key":"17_CR94","doi-asserted-by":"publisher","unstructured":"Zhang, C., Zou, Y., Li, Z., Yi, M., Wang, H.: TranSplat: Generalizable 3D Gaussian splatting from sparse multi-view images with transformers. In: AAAI. pp, 9869\u20139877 (2025). https:\/\/doi.org\/10.1609\/AAAI.V39I9.33070","DOI":"10.1609\/AAAI.V39I9.33070"},{"key":"17_CR95","doi-asserted-by":"publisher","unstructured":"Zhang, K., et al.: GS-LRM: Large reconstruction model for 3D Gaussian splatting. In: ECCV, vol. 15080, pp. 1\u201319 (2024). https:\/\/doi.org\/10.1007\/978-3-031-72670-5_1","DOI":"10.1007\/978-3-031-72670-5_1"},{"key":"17_CR96","doi-asserted-by":"publisher","unstructured":"Zhang, L., Liu, X., Martin, A.V., Bearfield, C.X., Brun, Y., Guan, H.: Attack-resilient image watermarking using stable diffusion. NeurIPS 38480\u201338507 (2024). https:\/\/doi.org\/10.52202\/079017-1215","DOI":"10.52202\/079017-1215"},{"key":"17_CR97","doi-asserted-by":"publisher","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: CVPR, pp. 3836\u20133847 (2023). https:\/\/doi.org\/10.1109\/ICCV51070.2023.00355","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"17_CR98","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.1109\/CVPR.2018.00068","DOI":"10.1109\/CVPR.2018.00068"},{"key":"17_CR99","doi-asserted-by":"publisher","unstructured":"Zheng, S., et al.: GPS-Gaussian: Generalizable pixel-wise 3D Gaussian splatting for real-time human novel view synthesis. In: CVPR, pp. 19680\u201319690 (2024). https:\/\/doi.org\/10.1109\/CVPR52733.2024.01861","DOI":"10.1109\/CVPR52733.2024.01861"},{"key":"17_CR100","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1145\/3197517.3201323","volume":"37","author":"T Zhou","year":"2018","unstructured":"Zhou, T., Tucker, R., Flynn, J., Fyffe, G., Snavely, N.: Stereo magnification: Learning view synthesis using multiplane images. ACM Trans. Graph. 37, 65 (2018). https:\/\/doi.org\/10.1145\/3197517.3201323","journal-title":"ACM Trans. Graph."},{"key":"17_CR101","doi-asserted-by":"publisher","unstructured":"Ziwen, C., et al.: Long-LRM: Long-sequence large reconstruction model for wide-coverage Gaussian splats. In: ICCV, pp. 4349\u20134359 (2025). https:\/\/doi.org\/10.1109\/ICCV51701.2025.00414","DOI":"10.1109\/ICCV51701.2025.00414"}],"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\/978-3-032-37464-6_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T10:29:58Z","timestamp":1789036198000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37464-6_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032374639","9783032374646"],"references-count":101,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37464-6_17","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"}}]}}