{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T07:03:50Z","timestamp":1790233430241,"version":"4.1.0"},"publisher-location":"Cham","reference-count":91,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370099","type":"print"},{"value":"9783032370105","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\/978-3-032-37010-5_15","type":"book-chapter","created":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T06:48:32Z","timestamp":1790232512000},"page":"266-284","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ROAR-3D: ROuting ARbitrary Views for\u00a0High-Fidelity 3D Generation"],"prefix":"10.1007","author":[{"given":"Hanxiao","family":"Sun","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingxin","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuhui","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zebin","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xintong","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongbo","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunchao","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenhan","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,25]]},"reference":[{"key":"15_CR1","unstructured":"Chang, J., et al.: Reconviagen: towards accurate multi-view 3d object reconstruction via generation (2025). https:\/\/arxiv.org\/abs\/2510.23306"},{"key":"15_CR2","doi-asserted-by":"crossref","unstructured":"Chen, D.Z., Siddiqui, Y., Lee, H.Y., Tulyakov, S., Nie\u00dfner, M.: Text2tex: text-driven texture synthesis via diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 18558\u201318568 (2023)","DOI":"10.1109\/ICCV51070.2023.01701"},{"key":"15_CR3","doi-asserted-by":"crossref","unstructured":"Chen, H., et al.: Single-stage diffusion nerf: a unified approach to 3d generation and reconstruction. In: ICCV, pp. 2416\u20132425 (2023)","DOI":"10.1109\/ICCV51070.2023.00229"},{"key":"15_CR4","doi-asserted-by":"crossref","unstructured":"Chen, R., Han, S., Xu, J., Su, H.: Point-based multi-view stereo network. In: ICCV, pp. 1538\u20131547 (2019)","DOI":"10.1109\/ICCV.2019.00162"},{"key":"15_CR5","unstructured":"Chen, Y., et al.: Ultra3d: efficient and high-fidelity 3d generation with part attention. arXiv preprint arXiv:2507.17745 (2025)"},{"key":"15_CR6","doi-asserted-by":"crossref","unstructured":"Cheng, S., et al.: Deep stereo using adaptive thin volume representation with uncertainty awareness. In: CVPR, pp. 2524\u20132534 (2020)","DOI":"10.1109\/CVPR42600.2020.00260"},{"key":"15_CR7","doi-asserted-by":"crossref","unstructured":"Deitke, M., et\u00a0al.: Objaverse-xl: a universe of 10m+ 3d objects. In: NeurIPS, vol. 36 (2024)","DOI":"10.52202\/075280-1554"},{"key":"15_CR8","doi-asserted-by":"crossref","unstructured":"Deitke, M., et al.: Objaverse: a universe of annotated 3d objects. In: ICCV, pp. 13142\u201313153 (2023)","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"15_CR9","doi-asserted-by":"crossref","unstructured":"Feng, Y., et al.: Romantex: decoupling 3d-aware rotary positional embedded multi-attention network for texture synthesis. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 17203\u201317213 (2025)","DOI":"10.1109\/ICCV51701.2025.01598"},{"key":"15_CR10","doi-asserted-by":"crossref","unstructured":"Furukawa, Y., Hern\u00e1ndez, C., et\u00a0al.: Multi-view stereo: a tutorial. Found. Trends\u00ae Comput. Graph. Vision 9(1-2), 1\u2013148 (2015)","DOI":"10.1561\/0600000052"},{"key":"15_CR11","doi-asserted-by":"crossref","unstructured":"Galliani, S., Lasinger, K., Schindler, K.: Massively parallel multiview stereopsis by surface normal diffusion. In: ICCV, pp. 873\u2013881 (2015)","DOI":"10.1109\/ICCV.2015.106"},{"key":"15_CR12","doi-asserted-by":"crossref","unstructured":"Gu, X., Fan, Z., Zhu, S., Dai, Z., Tan, F., Tan, P.: Cascade cost volume for high-resolution multi-view stereo and stereo matching. In: CVPR, pp. 2495\u20132504 (2020)","DOI":"10.1109\/CVPR42600.2020.00257"},{"key":"15_CR13","doi-asserted-by":"crossref","unstructured":"He, Z., et\u00a0al.: Materialmvp: illumination-invariant material generation via multi-view pbr diffusion. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 26294\u201326305 (2025)","DOI":"10.1109\/ICCV51701.2025.02440"},{"key":"15_CR14","unstructured":"Hitem3D Team: Hitem3d: High-quality 3d model generation service (2024). https:\/\/www.hitem3d.ai\/. Accessed 20 May 2024"},{"key":"15_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":"15_CR16","unstructured":"Hong, Y., et al.: Lrm: large reconstruction model for single image to 3d. In: ICLR (2023)"},{"key":"15_CR17","doi-asserted-by":"crossref","unstructured":"Huang, B., Yu, Z., Chen, A., Geiger, A., Gao, S.: 2d gaussian splatting for geometrically accurate radiance fields. In: ACM SIGGRAPH 2024 Conference Papers, pp. 1\u201311 (2024)","DOI":"10.1145\/3641519.3657428"},{"key":"15_CR18","doi-asserted-by":"crossref","unstructured":"Hui, K.H., Li, R., Hu, J., Fu, C.W.: Neural wavelet-domain diffusion for 3d shape generation. In: SIGGRAPH Aisa, pp. 1\u20139 (2022)","DOI":"10.1145\/3550469.3555394"},{"key":"15_CR19","unstructured":"Hunyuan3D, T., et al.: Hunyuan3d 2.1: from images to high-fidelity 3d assets with production-ready pbr material (2025). https:\/\/arxiv.org\/abs\/2506.15442"},{"key":"15_CR20","unstructured":"Hy-3D Team: Hy-3d (2024). https:\/\/hy-3d.com. Accessed 20 May 2024"},{"key":"15_CR21","unstructured":"Hyper3D Team: Hyper3d: High-fidelity 3d asset generation (2024). https:\/\/hyper3d.ai\/. Accessed 20 May 2024"},{"key":"15_CR22","unstructured":"Jang, E., Gu, S., Poole, B.: Categorical reparameterization with gumbel-softmax. arXiv preprint arXiv:1611.01144 (2016)"},{"issue":"4","key":"15_CR23","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3592433","volume":"42","author":"B Kerbl","year":"2023","unstructured":"Kerbl, B., Kopanas, G., Leimk\u00fchler, T., Drettakis, G.: 3d gaussian splatting for real-time radiance field rendering. TOG 42(4), 139\u20131 (2023)","journal-title":"TOG"},{"key":"15_CR24","first-page":"70990","volume":"38","author":"Z Kong","year":"2026","unstructured":"Kong, Z., et al.: Let them talk: audio-driven multi-person conversational video generation. Adv. Neural. Inf. Process. Syst. 38, 70990\u201371013 (2026)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"15_CR25","unstructured":"Lai, Z., et\u00a0al.: Hunyuan3d 2.5: towards high-fidelity 3d assets generation with ultimate details. arXiv preprint arXiv:2506.16504 (2025)"},{"key":"15_CR26","unstructured":"Lai, Z., et al.: Lattice: democratize high-fidelity 3d generation at scale. arXiv preprint arXiv:2512.03052 (2025)"},{"key":"15_CR27","unstructured":"Li, J., et al.: Instant3d: fast text-to-3d with sparse-view generation and large reconstruction model. arXiv preprint arXiv:2311.06214 (2023)"},{"key":"15_CR28","doi-asserted-by":"crossref","unstructured":"Li, P., et\u00a0al.: Era3d: high-resolution multiview diffusion using efficient row-wise attention. arXiv preprint arXiv:2405.11616 (2024)","DOI":"10.52202\/079017-1780"},{"key":"15_CR29","doi-asserted-by":"crossref","unstructured":"Li, P., et al.: Cmd: controllable multiview diffusion for 3d editing and progressive generation. In: Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers, pp. 1\u201310 (2025)","DOI":"10.1145\/3721238.3730722"},{"key":"15_CR30","doi-asserted-by":"crossref","unstructured":"Li, P., et\u00a0al.: Pshuman: photorealistic single-image 3d human reconstruction using cross-scale multiview diffusion and explicit remeshing. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 16008\u201316018 (2025)","DOI":"10.1109\/CVPR52734.2025.01492"},{"key":"15_CR31","doi-asserted-by":"crossref","unstructured":"Li, W., et al.: Craftsman: high-fidelity mesh generation with 3d native generation and interactive geometry refiner. arXiv preprint arXiv:2405.14979 (2024)","DOI":"10.1109\/CVPR52734.2025.00500"},{"key":"15_CR32","doi-asserted-by":"crossref","unstructured":"Li, Y., et\u00a0al.: Triposg: high-fidelity 3d shape synthesis using large-scale rectified flow models. arXiv preprint arXiv:2502.06608 (2025)","DOI":"10.1109\/TPAMI.2025.3633512"},{"key":"15_CR33","doi-asserted-by":"crossref","unstructured":"Lin, C.H., et al.: Magic3d: high-resolution text-to-3d content creation. In: CVPR, pp. 300\u2013309 (2023)","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"15_CR34","doi-asserted-by":"crossref","unstructured":"Lin, C.H., Ma, W.C., Torralba, A., Lucey, S.: Barf: bundle-adjusting neural radiance fields. In: ICCV, pp. 5741\u20135751 (2021)","DOI":"10.1109\/ICCV48922.2021.00569"},{"key":"15_CR35","unstructured":"Liu, G., et al.: Beyond vlm-based rewards: diffusion-native latent reward modeling. arXiv preprint arXiv:2602.11146 (2026)"},{"key":"15_CR36","doi-asserted-by":"crossref","unstructured":"Liu, M., et al.: One-2-3-45++: fast single image to 3d objects with consistent multi-view generation and 3d diffusion. In: CVPR, pp. 10072\u201310083 (2024)","DOI":"10.1109\/CVPR52733.2024.00960"},{"key":"15_CR37","doi-asserted-by":"crossref","unstructured":"Liu, M., et al.: One-2-3-45: any single image to 3d mesh in 45 seconds without per-shape optimization. In: NeurIPS, vol. 36 (2023)","DOI":"10.52202\/075280-0976"},{"key":"15_CR38","doi-asserted-by":"crossref","unstructured":"Liu, Y., Xie, M., Liu, H., Wong, T.T.: Text-guided texturing by synchronized multi-view diffusion. In: SIGGRAPH Asia 2024 Conference Papers, pp. 1\u201311 (2024)","DOI":"10.1145\/3680528.3687621"},{"key":"15_CR39","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"15_CR40","unstructured":"Luo, D., et al.: Matpedia: a universal generative foundation for high-fidelity material synthesis. arXiv preprint arXiv:2511.16957 (2025)"},{"key":"15_CR41","doi-asserted-by":"crossref","unstructured":"Luo, S., Hu, W.: Diffusion probabilistic models for 3d point cloud generation. In: CVPR, pp. 2837\u20132845 (2021)","DOI":"10.1109\/CVPR46437.2021.00286"},{"key":"15_CR42","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1007\/978-3-030-58452-8_24","volume-title":"Computer Vision \u2013 ECCV 2020","author":"B Mildenhall","year":"2020","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: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 405\u2013421. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_24"},{"key":"15_CR43","doi-asserted-by":"crossref","unstructured":"M\u00fcller, N., Siddiqui, Y., Porzi, L., Bulo, S.R., Kontschieder, P., Nie\u00dfner, M.: Diffrf: rendering-guided 3d radiance field diffusion. In: CVPR, pp. 4328\u20134338 (2023)","DOI":"10.1109\/CVPR52729.2023.00421"},{"key":"15_CR44","unstructured":"Nichol, A., Jun, H., Dhariwal, P., Mishkin, P., Chen, M.: Point-e: a system for generating 3d point clouds from complex prompts. arXiv preprint arXiv:2212.08751 (2022)"},{"key":"15_CR45","unstructured":"Oquab, M., et al.: Dinov2: learning robust visual features without supervision. Trans. Mach. Learn. Res. J. 1\u201331 (2024)"},{"key":"15_CR46","unstructured":"Poole, B., Jain, A., Barron, J.T., Mildenhall, B.: Dreamfusion: text-to-3d using 2d diffusion. arXiv preprint arXiv:2209.14988 (2022)"},{"key":"15_CR47","doi-asserted-by":"crossref","unstructured":"Qiu, L., et al.: Richdreamer: a generalizable normal-depth diffusion model for detail richness in text-to-3d. In: CVPR, pp. 9914\u20139925 (2024)","DOI":"10.1109\/CVPR52733.2024.00946"},{"key":"15_CR48","doi-asserted-by":"crossref","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)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"15_CR49","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"501","DOI":"10.1007\/978-3-319-46487-9_31","volume-title":"Computer Vision \u2013 ECCV 2016","author":"JL Sch\u00f6nberger","year":"2016","unstructured":"Sch\u00f6nberger, J.L., Zheng, E., Frahm, J.-M., Pollefeys, M.: Pixelwise view selection for unstructured multi-view stereo. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 501\u2013518. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46487-9_31"},{"key":"15_CR50","doi-asserted-by":"crossref","unstructured":"Shue, J.R., Chan, E.R., Po, R., Ankner, Z., Wu, J., Wetzstein, G.: 3d neural field generation using triplane diffusion. In: CVPR, pp. 20875\u201320886 (2023)","DOI":"10.1109\/CVPR52729.2023.02000"},{"key":"15_CR51","doi-asserted-by":"publisher","unstructured":"Sun, H., Gao, Y., Xie, J., Yang, J., Wang, B.: Svg-ir: spatially-varying gaussian splatting for inverse rendering. In: 2025 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 16143\u201316152 (2025). https:\/\/doi.org\/10.1109\/CVPR52734.2025.01505","DOI":"10.1109\/CVPR52734.2025.01505"},{"key":"15_CR52","doi-asserted-by":"publisher","unstructured":"Tang, J., Chen, Z., Chen, X., Wang, T., Zeng, G., Liu, Z.: Lgm: large multi-view gaussian model for high-resolution 3d content creation. In: ECCV, pp. 1\u201318. Springer, Heidelberg (2025). https:\/\/doi.org\/10.1007\/978-3-031-73235-5_1","DOI":"10.1007\/978-3-031-73235-5_1"},{"key":"15_CR53","unstructured":"Tang, J., Ren, J., Zhou, H., Liu, Z., Zeng, G.: Dreamgaussian: generative gaussian splatting for efficient 3d content creation. In: ICLR (2024)"},{"key":"15_CR54","doi-asserted-by":"crossref","unstructured":"Tang, J., et al.: Make-it-3d: high-fidelity 3d creation from a single image with diffusion prior. In: ICCV, pp. 22819\u201322829 (2023)","DOI":"10.1109\/ICCV51070.2023.02086"},{"key":"15_CR55","unstructured":"Tang, Z., et al.: Volumediffusion: flexible text-to-3d generation with efficient volumetric encoder. arXiv preprint arXiv:2312.11459 (2023)"},{"key":"15_CR56","unstructured":"Team, G., et al.: Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)"},{"key":"15_CR57","unstructured":"Tencent Hunyuan: Hunyuan3d (2024). https:\/\/3d.hunyuan.tencent.com\/"},{"key":"15_CR58","unstructured":"Tripo AI: Tripo: Fast 3d object generation from text and image (2024). https:\/\/www.tripo3d.ai\/. Accessed 20 May 2024"},{"key":"15_CR59","doi-asserted-by":"crossref","unstructured":"Wang, F., Galliani, S., Vogel, C., Speciale, P., Pollefeys, M.: Patchmatchnet: learned multi-view patchmatch stereo. In: CVPR, pp. 14194\u201314203 (2021)","DOI":"10.1109\/CVPR46437.2021.01397"},{"key":"15_CR60","doi-asserted-by":"crossref","unstructured":"Wang, J., Chen, M., Karaev, N., Vedaldi, A., Rupprecht, C., Novotny, D.: Vggt: visual geometry grounded transformer. arXiv preprint arXiv:2503.11651 (2025)","DOI":"10.1109\/CVPR52734.2025.00499"},{"key":"15_CR61","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":"15_CR62","doi-asserted-by":"crossref","unstructured":"Wang, T., et\u00a0al.: Rodin: a generative model for sculpting 3d digital avatars using diffusion. In: CVPR, pp. 4563\u20134573 (2023)","DOI":"10.1109\/CVPR52729.2023.00443"},{"key":"15_CR63","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: Prolificdreamer: high-fidelity and diverse text-to-3d generation with variational score distillation. In: NeurIPS, vol. 36 (2024)","DOI":"10.52202\/075280-0368"},{"key":"15_CR64","doi-asserted-by":"publisher","unstructured":"Wang, Z., et al.: Crm: single image to 3d textured mesh with convolutional reconstruction model. In: ECCV, pp. 57\u201374. Springer, Heidelberg (2025). https:\/\/doi.org\/10.1007\/978-3-031-72751-1_4","DOI":"10.1007\/978-3-031-72751-1_4"},{"key":"15_CR65","unstructured":"Wang, Z., Wu, S., Xie, W., Chen, M., Prisacariu, V.A.: Nerf-: neural radiance fields without known camera parameters (2021)"},{"key":"15_CR66","unstructured":"Wei, X., et al.: Meshlrm: large reconstruction model for high-quality mesh. arXiv preprint arXiv:2404.12385 (2024)"},{"key":"15_CR67","unstructured":"Wu, C.H., Chen, Y.C., Solarte, B., Yuan, L., Sun, M.: ifusion: inverting diffusion for pose-free reconstruction from sparse views. arXiv preprint arXiv:2312.17250 (2023)"},{"key":"15_CR68","doi-asserted-by":"crossref","unstructured":"Wu, K., et al.: Unique3d: high-quality and efficient 3d mesh generation from a single image. arXiv preprint arXiv:2405.20343 (2024)","DOI":"10.52202\/079017-3974"},{"key":"15_CR69","doi-asserted-by":"crossref","unstructured":"Wu, S., et al.: Direct3d: scalable image-to-3d generation via 3d latent diffusion transformer. arXiv preprint arXiv:2405.14832 (2024)","DOI":"10.52202\/079017-3873"},{"key":"15_CR70","unstructured":"Xiang, J., et al.: Native and compact structured latents for 3d generation (2025). https:\/\/arxiv.org\/abs\/2512.14692"},{"key":"15_CR71","doi-asserted-by":"crossref","unstructured":"Xiang, Jet al.: Structured 3d latents for scalable and versatile 3d generation. arXiv preprint arXiv:2412.01506 (2024)","DOI":"10.1109\/CVPR52734.2025.02000"},{"key":"15_CR72","doi-asserted-by":"publisher","unstructured":"Xu, C., et al.: Sparp: fast 3d object reconstruction and pose estimation from sparse views. In: ECCV. pp. 143\u2013163. Springer, Heidelberg (2024). https:\/\/doi.org\/10.1007\/978-3-031-73039-9_9","DOI":"10.1007\/978-3-031-73039-9_9"},{"key":"15_CR73","unstructured":"Xu, J., Cheng, W., Gao, Y., Wang, X., Gao, S., Shan, Y.: Instantmesh: efficient 3d mesh generation from a single image with sparse-view large reconstruction models. arXiv preprint arXiv:2404.07191 (2024)"},{"key":"15_CR74","doi-asserted-by":"crossref","unstructured":"Xu, Q., Tao, W.: Multi-scale geometric consistency guided multi-view stereo. In: CVPR, pp. 5483\u20135492 (2019)","DOI":"10.1109\/CVPR.2019.00563"},{"key":"15_CR75","doi-asserted-by":"crossref","unstructured":"Xu, Y., et al.: Grm: large gaussian reconstruction model for efficient 3d reconstruction and generation. arXiv preprint arXiv:2403.14621 (2024)","DOI":"10.1007\/978-3-031-72633-0_1"},{"key":"15_CR76","unstructured":"Xu, Y., et\u00a0al.: Dmv3d: denoising multi-view diffusion using 3d large reconstruction model. In: ICLR (2024)"},{"key":"15_CR77","doi-asserted-by":"crossref","unstructured":"Xue, L., et al.: Ulip: learning a unified representation of language, images, and point clouds for 3d understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1179\u20131189 (2023)","DOI":"10.1109\/CVPR52729.2023.00120"},{"key":"15_CR78","doi-asserted-by":"crossref","unstructured":"Yang, J., Mao, W., Alvarez, J.M., Liu, M.: Cost volume pyramid based depth inference for multi-view stereo. In: CVPR, pp. 4877\u20134886 (2020)","DOI":"10.1109\/CVPR42600.2020.00493"},{"key":"15_CR79","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"785","DOI":"10.1007\/978-3-030-01237-3_47","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Y Yao","year":"2018","unstructured":"Yao, Y., Luo, Z., Li, S., Fang, T., Quan, L.: MVSNet: depth inference for unstructured multi-view stereo. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11212, pp. 785\u2013801. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01237-3_47"},{"key":"15_CR80","doi-asserted-by":"crossref","unstructured":"Yao, Y., Luo, Z., Li, S., Shen, T., Fang, T., Quan, L.: Recurrent mvsnet for high-resolution multi-view stereo depth inference. In: CVPR, pp. 5525\u20135534 (2019)","DOI":"10.1109\/CVPR.2019.00567"},{"key":"15_CR81","doi-asserted-by":"crossref","unstructured":"Ye, C., et al.: Hi3dgen: high-fidelity 3d geometry generation from images via normal bridging, vol. 3. arXiv preprint arXiv:2503.22236 (2025)","DOI":"10.1109\/ICCV51701.2025.02323"},{"key":"15_CR82","unstructured":"Ye, Z., et al.: Unic: unified in-context video editing. arXiv preprint arXiv:2506.04216 (2025)"},{"key":"15_CR83","unstructured":"Ye, Z., et al.: Visual-aware cot: achieving high-fidelity visual consistency in unified models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9116\u20139126 (2026)"},{"issue":"4","key":"15_CR84","first-page":"1","volume":"42","author":"B Zhang","year":"2023","unstructured":"Zhang, B., Tang, J., Niessner, M., Wonka, P.: 3dshape2vecset: a 3d shape representation for neural fields and generative diffusion models. TOG 42(4), 1\u201316 (2023)","journal-title":"TOG"},{"key":"15_CR85","unstructured":"Zhang, B., et al.: Gaussiancube: structuring gaussian splatting using optimal transport for 3d generative modeling. arXiv e-prints pp. arXiv\u20132403 (2024)"},{"issue":"4","key":"15_CR86","first-page":"1","volume":"43","author":"L Zhang","year":"2024","unstructured":"Zhang, L., et al.: Clay: a controllable large-scale generative model for creating high-quality 3d assets. TOG 43(4), 1\u201320 (2024)","journal-title":"TOG"},{"key":"15_CR87","unstructured":"Zhao, Z., et\u00a0al.: Hunyuan3d 2.0: scaling diffusion models for high resolution textured 3d assets generation. arXiv preprint arXiv:2501.12202 (2025)"},{"key":"15_CR88","doi-asserted-by":"crossref","unstructured":"Zhao, Z., et al.: Michelangelo: conditional 3d shape generation based on shape-image-text aligned latent representation. In: NeurIPS, vol. 36 (2024)","DOI":"10.52202\/075280-3236"},{"key":"15_CR89","unstructured":"Zhou, J., Wang, J., Ma, B., Liu, Y.S., Huang, T., Wang, X.: Uni3d: exploring unified 3d representation at scale. In: International Conference on Learning Representations (ICLR) (2024)"},{"key":"15_CR90","doi-asserted-by":"crossref","unstructured":"Zhou, L., Du, Y., Wu, J.: 3d shape generation and completion through point-voxel diffusion. In: ICCV, pp. 5826\u20135835 (2021)","DOI":"10.1109\/ICCV48922.2021.00577"},{"key":"15_CR91","unstructured":"Zuo, Q., et\u00a0al.: Videomv: consistent multi-view generation based on large video generative model. arXiv preprint arXiv:2403.12010 (2024)"}],"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\/978-3-032-37010-5_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T06:48:52Z","timestamp":1790232532000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37010-5_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370099","9783032370105"],"references-count":91,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37010-5_15","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":"25 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"}}]}}