{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T01:01:13Z","timestamp":1778115673292,"version":"3.51.4"},"publisher-location":"Cham","reference-count":97,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031730382","type":"print"},{"value":"9783031730399","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-73039-9_9","type":"book-chapter","created":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T14:57:07Z","timestamp":1730300227000},"page":"143-163","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["SpaRP: Fast 3D Object Reconstruction and\u00a0Pose Estimation from\u00a0Sparse Views"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-0574-5357","authenticated-orcid":false,"given":"Chao","family":"Xu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linghao","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yulin","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruoxi","family":"Shi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Su","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minghua","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,31]]},"reference":[{"issue":"3","key":"9_CR1","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1145\/1531326.1531330","volume":"28","author":"C Barnes","year":"2009","unstructured":"Barnes, C., Shechtman, E., Finkelstein, A., Goldman, D.B.: PatchMatch: a randomized correspondence algorithm for structural image editing. ACM Trans. Graph. 28(3), 24 (2009)","journal-title":"ACM Trans. Graph."},{"key":"9_CR2","unstructured":"Bradski, G.: Perspective-n-Point (PnP) pose computation (the openCV library) (2000). https:\/\/docs.opencv.org\/4.x\/d5\/d1f\/calib3d_solvePnP.html"},{"key":"9_CR3","doi-asserted-by":"crossref","unstructured":"Chan, E.R., et al.: GeNVS: generative novel view synthesis with 3D-aware diffusion models (2023)","DOI":"10.1109\/ICCV51070.2023.00389"},{"key":"9_CR4","doi-asserted-by":"crossref","unstructured":"Chen, A., et al.: MVSNeRF: fast generalizable radiance field reconstruction from multi-view stereo. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 14124\u201314133 (2021)","DOI":"10.1109\/ICCV48922.2021.01386"},{"key":"9_CR5","doi-asserted-by":"crossref","unstructured":"Chen, R., Chen, Y., Jiao, N., Jia, K.: Fantasia3D: disentangling geometry and appearance for high-quality text-to-3D content creation. arXiv preprint arXiv:2303.13873 (2023)","DOI":"10.1109\/ICCV51070.2023.02033"},{"key":"9_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Z., Wang, F., Liu, H.: Text-to-3D using gaussian splatting. arXiv preprint arXiv:2309.16585 (2023)","DOI":"10.1109\/CVPR52733.2024.02022"},{"key":"9_CR7","doi-asserted-by":"crossref","unstructured":"Collins, J., et\u00a0al.: ABO: dataset and benchmarks for real-world 3D object understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21126\u201321136 (2022)","DOI":"10.1109\/CVPR52688.2022.02045"},{"key":"9_CR8","doi-asserted-by":"crossref","unstructured":"Deitke, M., et\u00a0al.: Objaverse-XL: a universe of 10m+ 3D objects. arXiv preprint arXiv:2307.05663 (2023)","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"9_CR9","doi-asserted-by":"crossref","unstructured":"Deitke, M., et al.: Objaverse: a universe of annotated 3D objects. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13142\u201313153 (2023)","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"9_CR10","doi-asserted-by":"crossref","unstructured":"Deng, C., et\u00a0al.: NeRDi: single-view nerf synthesis with language-guided diffusion as general image priors. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20637\u201320647 (2023)","DOI":"10.1109\/CVPR52729.2023.01977"},{"key":"9_CR11","unstructured":"Denninger, M., et al.: BlenderProc. arXiv preprint arXiv:1911.01911 (2019)"},{"key":"9_CR12","doi-asserted-by":"crossref","unstructured":"Downs, L., et al.: Google scanned objects: a high-quality dataset of 3D scanned household items. In: 2022 International Conference on Robotics and Automation (ICRA), pp. 2553\u20132560. IEEE (2022)","DOI":"10.1109\/ICRA46639.2022.9811809"},{"key":"9_CR13","unstructured":"Guo, Y.C., et al.: threestudio: a unified framework for 3D content generation (2023). https:\/\/github.com\/threestudio-project\/threestudio"},{"key":"9_CR14","unstructured":"Hong, Y., et al.: LRM: large reconstruction model for single image to 3D. arXiv preprint arXiv:2311.04400 (2023)"},{"key":"9_CR15","doi-asserted-by":"crossref","unstructured":"Jain, A., Mildenhall, B., Barron, J.T., Abbeel, P., Poole, B.: Zero-shot text-guided object generation with dream fields. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 867\u2013876 (2022)","DOI":"10.1109\/CVPR52688.2022.00094"},{"key":"9_CR16","doi-asserted-by":"crossref","unstructured":"Jain, A., Tancik, M., Abbeel, P.: Putting nerf on a diet: semantically consistent few-shot view synthesis. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5885\u20135894 (2021)","DOI":"10.1109\/ICCV48922.2021.00583"},{"key":"9_CR17","unstructured":"Jiang, H., Jiang, Z., Grauman, K., Zhu, Y.: Few-view object reconstruction with unknown categories and camera poses. arXiv preprint arXiv:2212.04492 (2022)"},{"key":"9_CR18","unstructured":"Jiang, H., Jiang, Z., Zhao, Y., Huang, Q.: Leap: liberate sparse-view 3D modeling from camera poses. arXiv preprint arXiv:2310.01410 (2023)"},{"key":"9_CR19","doi-asserted-by":"crossref","unstructured":"Johari, M.M., Lepoittevin, Y., Fleuret, F.: GeoNeRF: generalizing nerf with geometry priors. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18365\u201318375 (2022)","DOI":"10.1109\/CVPR52688.2022.01782"},{"key":"9_CR20","unstructured":"Jun, H., Nichol, A.: Shap-E: generating conditional 3D implicit functions. arXiv preprint arXiv:2305.02463 (2023)"},{"key":"9_CR21","doi-asserted-by":"crossref","unstructured":"Karnewar, A., Vedaldi, A., Novotny, D., Mitra, N.J.: HOLODIFFUSION: training a 3D diffusion model using 2D images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18423\u201318433 (2023)","DOI":"10.1109\/CVPR52729.2023.01767"},{"key":"9_CR22","doi-asserted-by":"crossref","unstructured":"Kim, M., Seo, S., Han, B.: InfoNeRF: ray entropy minimization for few-shot neural volume rendering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12912\u201312921 (2022)","DOI":"10.1109\/CVPR52688.2022.01257"},{"key":"9_CR23","doi-asserted-by":"crossref","unstructured":"Kong, X., Liu, S., Lyu, X., Taher, M., Qi, X., Davison, A.J.: EscherNet: a generative model for scalable view synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9503\u20139513 (2024)","DOI":"10.1109\/CVPR52733.2024.00908"},{"key":"9_CR24","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"198","DOI":"10.1007\/978-3-031-19784-0_12","volume-title":"ECCV 2022","author":"J Kulh\u00e1nek","year":"2022","unstructured":"Kulh\u00e1nek, J., Derner, E., Sattler, T., Babu\u0161ka, R.: ViewFormer: Nerf-free neural rendering from few images using transformers. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13675, pp. 198\u2013216. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19784-0_12"},{"key":"9_CR25","doi-asserted-by":"crossref","unstructured":"Lai, Z., Liu, S., Efros, A.A., Wang, X.: Video autoencoder: self-supervised disentanglement of static 3d structure and motion. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9730\u20139740 (2021)","DOI":"10.1109\/ICCV48922.2021.00959"},{"issue":"6","key":"9_CR26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3414685.3417861","volume":"39","author":"S Laine","year":"2020","unstructured":"Laine, S., Hellsten, J., Karras, T., Seol, Y., Lehtinen, J., Aila, T.: Modular primitives for high-performance differentiable rendering. ACM Trans. Graph. 39(6), 1\u201314 (2020)","journal-title":"ACM Trans. Graph."},{"key":"9_CR27","unstructured":"Lee, H.H., Chang, A.X.: Understanding pure clip guidance for voxel grid nerf models. arXiv preprint arXiv:2209.15172 (2022)"},{"key":"9_CR28","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":"9_CR29","doi-asserted-by":"crossref","unstructured":"Lin, A., Zhang, J.Y., Ramanan, D., Tulsiani, S.: RelPose++: recovering 6D poses from sparse-view observations. arXiv preprint arXiv:2305.04926 (2023)","DOI":"10.1109\/3DV62453.2024.00126"},{"key":"9_CR30","doi-asserted-by":"crossref","unstructured":"Lin, C.H., et al.: Magic3D: high-resolution text-to-3D content creation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 300\u2013309 (2023)","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"9_CR31","doi-asserted-by":"crossref","unstructured":"Lin, C.H., Ma, W.C., Torralba, A., Lucey, S.: BARF: bundle-adjusting neural radiance fields. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5741\u20135751 (2021)","DOI":"10.1109\/ICCV48922.2021.00569"},{"key":"9_CR32","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10072\u201310083 (2024)","DOI":"10.1109\/CVPR52733.2024.00960"},{"key":"9_CR33","unstructured":"Liu, M., et al.: OpenShape: scaling up 3D shape representation towards open-world understanding. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"9_CR34","unstructured":"Liu, M., et al.: One-2-3-45: any single image to 3D mesh in 45 seconds without per-shape optimization. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"9_CR35","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: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9298\u20139309 (2023)","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"9_CR36","unstructured":"Liu, Y., et al.: SyncDreamer: generating multiview-consistent images from a single-view image. arXiv preprint arXiv:2309.03453 (2023)"},{"key":"9_CR37","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: Neural rays for occlusion-aware image-based rendering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7824\u20137833 (2022)","DOI":"10.1109\/CVPR52688.2022.00767"},{"key":"9_CR38","doi-asserted-by":"crossref","unstructured":"Long, X., et\u00a0al.: Wonder3D: single image to 3D using cross-domain diffusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9970\u20139980 (2024)","DOI":"10.1109\/CVPR52733.2024.00951"},{"key":"9_CR39","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"210","DOI":"10.1007\/978-3-031-19824-3_13","volume-title":"ECCV 2022","author":"X Long","year":"2022","unstructured":"Long, X., Lin, C., Wang, P., Komura, T., Wang, W.: SparseNeuS: fast generalizable neural surface reconstruction from sparse views. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13692, pp. 210\u2013227. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19824-3_13"},{"key":"9_CR40","doi-asserted-by":"crossref","unstructured":"Melas-Kyriazi, L., Laina, I., Rupprecht, C., Vedaldi, A.: RealFusion: 360deg reconstruction of any object from a single image. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8446\u20138455 (2023)","DOI":"10.1109\/CVPR52729.2023.00816"},{"key":"9_CR41","doi-asserted-by":"crossref","unstructured":"Metzer, G., Richardson, E., Patashnik, O., Giryes, R., Cohen-Or, D.: Latent-NeRF for shape-guided generation of 3D shapes and textures. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12663\u201312673 (2023)","DOI":"10.1109\/CVPR52729.2023.01218"},{"key":"9_CR42","doi-asserted-by":"crossref","unstructured":"Michel, O., Bar-On, R., Liu, R., Benaim, S., Hanocka, R.: Text2Mesh: text-driven neural stylization for meshes. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13492\u201313502 (2022)","DOI":"10.1109\/CVPR52688.2022.01313"},{"issue":"1","key":"9_CR43","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1145\/3503250","volume":"65","author":"B Mildenhall","year":"2021","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. Commun. ACM 65(1), 99\u2013106 (2021)","journal-title":"Commun. ACM"},{"key":"9_CR44","doi-asserted-by":"crossref","unstructured":"Mohammad\u00a0Khalid, N., Xie, T., Belilovsky, E., Popa, T.: Clip-mesh: generating textured meshes from text using pretrained image-text models. In: SIGGRAPH Asia 2022 Conference Papers, pp.\u00a01\u20138 (2022)","DOI":"10.1145\/3550469.3555392"},{"key":"9_CR45","doi-asserted-by":"crossref","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5480\u20135490 (2022)","DOI":"10.1109\/CVPR52688.2022.00540"},{"key":"9_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":"9_CR47","unstructured":"Qian, G., et\u00a0al.: Magic123: one image to high-quality 3D object generation using both 2D and 3D diffusion priors. arXiv preprint arXiv:2306.17843 (2023)"},{"key":"9_CR48","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"9_CR49","doi-asserted-by":"crossref","unstructured":"Raj, A., et\u00a0al.: DreamBooth3D: subject-driven text-to-3D generation. arXiv preprint arXiv:2303.13508 (2023)","DOI":"10.1109\/ICCV51070.2023.00223"},{"key":"9_CR50","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: International Conference on Machine Learning, pp. 8821\u20138831. PMLR (2021)"},{"key":"9_CR51","unstructured":"Rematas, K., Martin-Brualla, R., Ferrari, V.: ShaRF: shape-conditioned radiance fields from a single view. arXiv preprint arXiv:2102.08860 (2021)"},{"key":"9_CR52","doi-asserted-by":"crossref","unstructured":"Ren, Y., Zhang, T., Pollefeys, M., S\u00fcsstrunk, S., Wang, F.: VolRecon: volume rendering of signed ray distance functions for generalizable multi-view reconstruction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16685\u201316695 (2023)","DOI":"10.1109\/CVPR52729.2023.01601"},{"key":"9_CR53","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"9_CR54","first-page":"36479","volume":"35","author":"C Saharia","year":"2022","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. Adv. Neural. Inf. Process. Syst. 35, 36479\u201336494 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"9_CR55","doi-asserted-by":"crossref","unstructured":"Sajjadi, M.S., et\u00a0al.: Scene representation transformer: geometry-free novel view synthesis through set-latent scene representations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6229\u20136238 (2022)","DOI":"10.1109\/CVPR52688.2022.00613"},{"key":"9_CR56","doi-asserted-by":"crossref","unstructured":"Schonberger, J.L., Frahm, J.M.: Structure-from-motion revisited. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4104\u20134113 (2016)","DOI":"10.1109\/CVPR.2016.445"},{"key":"9_CR57","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, Part III. LNCS, vol. 9907, pp. 501\u2013518. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46487-9_31"},{"key":"9_CR58","doi-asserted-by":"crossref","unstructured":"Sch\u00f6nberger, J.L., Frahm, J.M.: Structure-from-motion revisited. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.445"},{"key":"9_CR59","unstructured":"Seo, J., et al.: Let 2D diffusion model know 3D-consistency for robust text-to-3D generation. arXiv preprint arXiv:2303.07937 (2023)"},{"key":"9_CR60","unstructured":"Shi, R., et al.: Zero123++: a single image to consistent multi-view diffusion base model. arXiv preprint arXiv:2310.15110 (2023)"},{"key":"9_CR61","doi-asserted-by":"crossref","unstructured":"Shi, R., Wei, X., Wang, C., Su, H.: ZeroRF: fast sparse view $$360^{\\circ }$$ reconstruction with zero pretraining. arXiv preprint arXiv:2312.09249 (2023)","DOI":"10.1109\/CVPR52733.2024.01995"},{"key":"9_CR62","unstructured":"Shi, Y., et al.: MVDream: multi-view diffusion for 3d generation. arXiv preprint arXiv:2308.16512 (2023)"},{"key":"9_CR63","doi-asserted-by":"crossref","unstructured":"Sinha, S., Zhang, J.Y., Tagliasacchi, A., Gilitschenski, I., Lindell, D.B.: SparsePose: sparse-view camera pose regression and refinement. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21349\u201321359 (2023)","DOI":"10.1109\/CVPR52729.2023.02045"},{"issue":"8","key":"9_CR64","doi-asserted-by":"publisher","first-page":"1362","DOI":"10.1109\/TPAMI.2009.161","volume":"32","author":"RM Stereopsis","year":"2010","unstructured":"Stereopsis, R.M.: Accurate, dense, and robust multiview stereopsis. IEEE Trans. Pattern Anal. Mach. Intell. 32(8), 1362\u20131376 (2010)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"9_CR65","doi-asserted-by":"crossref","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. arXiv preprint arXiv:2402.05054 (2024)","DOI":"10.1007\/978-3-031-73235-5_1"},{"key":"9_CR66","unstructured":"Tang, J., Ren, J., Zhou, H., Liu, Z., Zeng, G.: DreamGaussian: generative Gaussian splatting for efficient 3D content creation. arXiv preprint arXiv:2309.16653 (2023)"},{"key":"9_CR67","doi-asserted-by":"crossref","unstructured":"Tang, J., et al.: Make-it-3D: high-fidelity 3D creation from a single image with diffusion prior. arXiv preprint arXiv:2303.14184 (2023)","DOI":"10.1109\/ICCV51070.2023.02086"},{"key":"9_CR68","unstructured":"Tewari, A., et al.: Diffusion with forward models: solving stochastic inverse problems without direct supervision. arXiv preprint arXiv:2306.11719 (2023)"},{"key":"9_CR69","unstructured":"Tochilkin, D., et al.: TripoSR: fast 3D object reconstruction from a single image (2024)"},{"key":"9_CR70","doi-asserted-by":"crossref","unstructured":"Trevithick, A., Yang, B.: GRF: learning a general radiance field for 3D representation and rendering. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15182\u201315192 (2021)","DOI":"10.1109\/ICCV48922.2021.01490"},{"key":"9_CR71","doi-asserted-by":"crossref","unstructured":"Truong, P., Rakotosaona, M.J., Manhardt, F., Tombari, F.: SPARF: neural radiance fields from sparse and noisy poses. In: CVF Conference on Computer Vision and Pattern Recognition, CVPR, vol.\u00a01 (2023)","DOI":"10.1109\/CVPR52729.2023.00408"},{"key":"9_CR72","doi-asserted-by":"crossref","unstructured":"Tung, H.Y.F., Cheng, R., Fragkiadaki, K.: Learning spatial common sense with geometry-aware recurrent networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2595\u20132603 (2019)","DOI":"10.1109\/CVPR.2019.00270"},{"key":"9_CR73","doi-asserted-by":"crossref","unstructured":"Wang, H., Du, X., Li, J., Yeh, R.A., Shakhnarovich, G.: Score Jacobian chaining: lifting pretrained 2D diffusion models for 3D generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12619\u201312629 (2023)","DOI":"10.1109\/CVPR52729.2023.01214"},{"key":"9_CR74","doi-asserted-by":"crossref","unstructured":"Wang, H., Sridhar, S., Huang, J., Valentin, J., Song, S., Guibas, L.J.: Normalized object coordinate space for category-level 6d object pose and size estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2642\u20132651 (2019)","DOI":"10.1109\/CVPR.2019.00275"},{"key":"9_CR75","doi-asserted-by":"crossref","unstructured":"Wang, J., Rupprecht, C., Novotny, D.: PoseDiffusion: solving pose estimation via diffusion-aided bundle adjustment. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9773\u20139783 (2023)","DOI":"10.1109\/ICCV51070.2023.00896"},{"key":"9_CR76","unstructured":"Wang, P., et\u00a0al.: Is attention all NeRF needs? arXiv preprint arXiv:2207.13298 (2022)"},{"key":"9_CR77","unstructured":"Wang, P., Liu, L., Liu, Y., Theobalt, C., Komura, T., Wang, W.: NeuS: learning neural implicit surfaces by volume rendering for multi-view reconstruction. arXiv preprint arXiv:2106.10689 (2021)"},{"key":"9_CR78","unstructured":"Wang, P., et al.: PF-LRM: pose-free large reconstruction model for joint pose and shape prediction. arXiv preprint arXiv:2311.12024 (2023)"},{"key":"9_CR79","doi-asserted-by":"crossref","unstructured":"Wang, Q., et al.: IBRNet: learning multi-view image-based rendering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4690\u20134699 (2021)","DOI":"10.1109\/CVPR46437.2021.00466"},{"key":"9_CR80","unstructured":"Wang, Z., et al.: ProlificDreamer: high-fidelity and diverse text-to-3D generation with variational score distillation. arXiv preprint arXiv:2305.16213 (2023)"},{"key":"9_CR81","unstructured":"Wang, Z., Wu, S., Xie, W., Chen, M., Prisacariu, V.A.: NeRF\u2013: neural radiance fields without known camera parameters. arXiv preprint arXiv:2102.07064 (2021)"},{"key":"9_CR82","unstructured":"Weng, H., et al.: Consistent123: improve consistency for one image to 3D object synthesis. arXiv preprint arXiv:2310.08092 (2023)"},{"key":"9_CR83","unstructured":"Wu, C.H., Chen, Y.C., Solarte, B., Yuan, L., Sun, M.: iFusion: inverting diffusion for pose-free reconstruction from sparse views (2023)"},{"key":"9_CR84","doi-asserted-by":"crossref","unstructured":"Wu, R., et\u00a0al.: ReconFusion: 3D reconstruction with diffusion priors. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21551\u201321561 (2024)","DOI":"10.1109\/CVPR52733.2024.02036"},{"key":"9_CR85","doi-asserted-by":"crossref","unstructured":"Wu, T., et\u00a0al.: OmniObject3D: large-vocabulary 3D object dataset for realistic perception, reconstruction and generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 803\u2013814 (2023)","DOI":"10.1109\/CVPR52729.2023.00084"},{"key":"9_CR86","unstructured":"Xia, Y., Tang, H., Timofte, R., Van\u00a0Gool, L.: SiNeRF: sinusoidal neural radiance fields for joint pose estimation and scene reconstruction. arXiv preprint arXiv:2210.04553 (2022)"},{"key":"9_CR87","doi-asserted-by":"crossref","unstructured":"Xu, D., Jiang, Y., Wang, P., Fan, Z., Wang, Y., Wang, Z.: NeuralLift-360: lifting an in-the-wild 2D photo to a 3D object with 360deg views. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4479\u20134489 (2023)","DOI":"10.1109\/CVPR52729.2023.00435"},{"key":"9_CR88","doi-asserted-by":"crossref","unstructured":"Xu, J., et al.: Dream3D: zero-shot text-to-3D synthesis using 3D shape prior and text-to-image diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20908\u201320918 (2023)","DOI":"10.1109\/CVPR52729.2023.02003"},{"key":"9_CR89","doi-asserted-by":"crossref","unstructured":"Yang, H., et al.: ContraNeRF: generalizable neural radiance fields for synthetic-to-real novel view synthesis via contrastive learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16508\u201316517 (2023)","DOI":"10.1109\/CVPR52729.2023.01584"},{"key":"9_CR90","doi-asserted-by":"crossref","unstructured":"Yang, Z., Ren, Z., Bautista, M.A., Zhang, Z., Shan, Q., Huang, Q.: FvOR: robust joint shape and pose optimization for few-view object reconstruction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2497\u20132507 (2022)","DOI":"10.1109\/CVPR52688.2022.00253"},{"key":"9_CR91","first-page":"4805","volume":"34","author":"L Yariv","year":"2021","unstructured":"Yariv, L., Gu, J., Kasten, Y., Lipman, Y.: Volume rendering of neural implicit surfaces. Adv. Neural. Inf. Process. Syst. 34, 4805\u20134815 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"9_CR92","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. arXiv preprint arXiv:2310.03020 (2023)","DOI":"10.1109\/3DV62453.2024.00027"},{"key":"9_CR93","doi-asserted-by":"crossref","unstructured":"Yu, A., Ye, V., Tancik, M., Kanazawa, A.: pixelNeRF: neural radiance fields from one or few images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4578\u20134587 (2021)","DOI":"10.1109\/CVPR46437.2021.00455"},{"key":"9_CR94","doi-asserted-by":"crossref","unstructured":"Yu, C., Zhou, Q., Li, J., Zhang, Z., Wang, Z., Wang, F.: Points-to-3D: bridging the gap between sparse points and shape-controllable text-to-3D generation. arXiv preprint arXiv:2307.13908 (2023)","DOI":"10.1145\/3581783.3612232"},{"key":"9_CR95","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"592","DOI":"10.1007\/978-3-031-19821-2_34","volume-title":"ECCV 2022","author":"JY Zhang","year":"2022","unstructured":"Zhang, J.Y., Ramanan, D., Tulsiani, S.: RelPose: predicting probabilistic relative rotation for single objects in the wild. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. Lecture Notes in Computer Science, vol. 13691, pp. 592\u2013611. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19821-2_34"},{"key":"9_CR96","unstructured":"Zhang, L.: Reference-only control (2023). https:\/\/github.com\/Mikubill\/sd-webui-controlnet\/discussions\/1236"},{"key":"9_CR97","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Tulsiani, S.: SparseFusion: distilling view-conditioned diffusion for 3D reconstruction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12588\u201312597 (2023)","DOI":"10.1109\/CVPR52729.2023.01211"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73039-9_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T15:21:31Z","timestamp":1730301691000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73039-9_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,31]]},"ISBN":["9783031730382","9783031730399"],"references-count":97,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73039-9_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,31]]},"assertion":[{"value":"31 October 2024","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}