{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T06:32:34Z","timestamp":1773469954595,"version":"3.50.1"},"publisher-location":"Cham","reference-count":101,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031732348","type":"print"},{"value":"9783031732355","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"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\/978-3-031-73235-5_7","type":"book-chapter","created":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T06:01:53Z","timestamp":1727589713000},"page":"112-130","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":30,"title":["LN3Diff: Scalable Latent Neural Fields Diffusion for\u00a0Speedy 3D Generation"],"prefix":"10.1007","author":[{"given":"Yushi","family":"Lan","sequence":"first","affiliation":[]},{"given":"Fangzhou","family":"Hong","sequence":"additional","affiliation":[]},{"given":"Shuai","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Shangchen","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Xuyi","family":"Meng","sequence":"additional","affiliation":[]},{"given":"Bo","family":"Dai","sequence":"additional","affiliation":[]},{"given":"Xingang","family":"Pan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5345-1591","authenticated-orcid":false,"given":"Chen Change","family":"Loy","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,9,30]]},"reference":[{"key":"7_CR1","doi-asserted-by":"crossref","unstructured":"Anciukevi\u010dius, T., et al.: RenderDiffusion: image diffusion for 3d reconstruction, inpainting and generation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01213"},{"key":"7_CR2","unstructured":"Bi\u0144kowski, M., Sutherland, D.J., Arbel, M., Gretton, A.: Demystifying MMD GANs. In: ICLR (2018)"},{"key":"7_CR3","unstructured":"Brock, A., Donahue, J., Simonyan, K.: Large scale GAN training for high fidelity natural image synthesis. In: ICLR (2019)"},{"key":"7_CR4","doi-asserted-by":"crossref","unstructured":"Cai, S., Obukhov, A., Dai, D., Van\u00a0Gool, L.: Pix2NeRF: unsupervised conditional p-GAN for single image to neural radiance fields translation. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00395"},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"Chan, E., Monteiro, M., Kellnhofer, P., Wu, J., Wetzstein, G.: Pi-GAN: periodic implicit generative adversarial networks for 3D-aware image synthesis. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00574"},{"key":"7_CR6","doi-asserted-by":"crossref","unstructured":"Chan, E.R., et al.: Efficient geometry-aware 3D generative adversarial networks. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01565"},{"key":"7_CR7","doi-asserted-by":"crossref","unstructured":"Chan, E.R., et al.: GeNVS: generative novel view synthesis with 3D-aware diffusion models. arXiv (2023)","DOI":"10.1109\/ICCV51070.2023.00389"},{"key":"7_CR8","unstructured":"Chang, A.X., et al.: ShapeNet: an information-rich 3D model repository. arXiv preprint arXiv:1512.03012 (2015)"},{"key":"7_CR9","doi-asserted-by":"crossref","unstructured":"Chen, H., et al.: Single-stage diffusion nerf: a unified approach to 3D generation and reconstruction. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00229"},{"key":"7_CR10","doi-asserted-by":"crossref","unstructured":"Chen, Y., Wang, T., Wu, T., Pan, X., Jia, K., Liu, Z.: Comboverse: compositional 3d assets creation using spatially-aware diffusion guidance. arXiv preprint arXiv:2403.12409 (2024)","DOI":"10.1007\/978-3-031-72691-0_8"},{"key":"7_CR11","unstructured":"Contributors, S.: SpConv: spatially sparse convolution library (2022). https:\/\/github.com\/traveller59\/spconv"},{"key":"7_CR12","doi-asserted-by":"crossref","unstructured":"Deitke, M., et al.: Objaverse-xl: a universe of 10m+ 3d objects. arXiv preprint arXiv:2307.05663 (2023)","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"Deitke, M., et al.: Objaverse: a universe of annotated 3D objects. arXiv preprint arXiv:2212.08051 (2022)","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"7_CR14","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat gans on image synthesis. In: NeurIPS (2021)"},{"key":"7_CR15","unstructured":"Dosovitskiy, A., et al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"7_CR16","unstructured":"Dupont, E., Kim, H., Eslami, S.M.A., Rezende, D.J., Rosenbaum, D.: From data to functa: your data point is a function and you can treat it like one. In: ICML (2022)"},{"key":"7_CR17","doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R., Ommer, B.: Taming transformers for high-resolution image synthesis. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"7_CR18","unstructured":"Gao, J., et al.: Get3D: a generative model of high quality 3D textured shapes learned from images. In: NeurIPS (2022)"},{"key":"7_CR19","unstructured":"Goodfellow, I.J., et al.: Generative adversarial nets. In: NeurIPS (2014)"},{"key":"7_CR20","doi-asserted-by":"crossref","unstructured":"Gu, J., Gao, Q., Zhai, S., Chen, B., Liu, L., Susskind, J.: Learning controllable 3D diffusion models from single-view images. arXiv preprint arXiv:2304.06700 (2023)","DOI":"10.1109\/3DV62453.2024.00030"},{"key":"7_CR21","unstructured":"Gu, J., Liu, L., Wang, P., Theobalt, C.: StyleNeRF: a style-based 3D-aware generator for high-resolution image synthesis. In: ICLR (2021)"},{"key":"7_CR22","unstructured":"Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., Courville, A.C.: Improved training of wasserstein GANs. In: NeurIPS (2017)"},{"key":"7_CR23","unstructured":"Gupta, A., Xiong, W., Nie, Y., Jones, I., O\u011fuz, B.: 3dgen: triplane latent diffusion for textured mesh generation (2023). https:\/\/arxiv.org\/abs\/2303.05371"},{"key":"7_CR24","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u2019ar, P., Girshick, R.B.: Masked autoencoders are scalable vision learners. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"7_CR25","doi-asserted-by":"crossref","unstructured":"Henzler, P., Mitra, N.J., Ritschel, T.: Escaping plato\u2019s cave: 3D shape from adversarial rendering. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.01008"},{"key":"7_CR26","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. In: NeurIPS (2017)"},{"key":"7_CR27","unstructured":"Ho, J.: Classifier-free diffusion guidance. In: NeurIPS (2021)"},{"key":"7_CR28","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: NeurIPS (2020)"},{"key":"7_CR29","unstructured":"Hong, F., Chen, Z., Lan, Y., Pan, L., Liu, Z.: EVA3D: compositional 3D human generation from 2d image collections. In: ICLR (2022)"},{"key":"7_CR30","unstructured":"Hong, Y., et al.: LRM: large reconstruction model for single image to 3D. In: ICLR (2024)"},{"key":"7_CR31","unstructured":"Hoogeboom, E., Heek, J., Salimans, T.: simple diffusion: end-to-end diffusion for high resolution images. In: ICML (2023)"},{"key":"7_CR32","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: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00094"},{"key":"7_CR33","unstructured":"Jun, H., Nichol, A.: Shap-E: Generating conditional 3D implicit functions. arXiv preprint arXiv:2305.02463 (2023)"},{"key":"7_CR34","unstructured":"Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of GANs for improved quality, stability, and variation. In: ICLR (2018)"},{"key":"7_CR35","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"7_CR36","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., Aila, T.: Analyzing and improving the image quality of StyleGAN. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"7_CR37","doi-asserted-by":"crossref","unstructured":"Kato, H., Harada, T.: Learning view priors for single-view 3D reconstruction. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01001"},{"issue":"4","key":"7_CR38","doi-asserted-by":"publisher","first-page":"1","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. ACM Trans. Graph. 42(4), 1\u201314 (2023)","journal-title":"ACM Trans. Graph."},{"key":"7_CR39","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv (2013)"},{"key":"7_CR40","unstructured":"Kosiorek, A.R., et al.: NeRF-VAE: a geometry aware 3D scene generative model. In: ICML (2021)"},{"key":"7_CR41","doi-asserted-by":"crossref","unstructured":"Kumari, N., Zhang, R., Shechtman, E., Zhu, J.Y.: Ensembling off-the-shelf models for gan training. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01039"},{"key":"7_CR42","doi-asserted-by":"publisher","first-page":"611","DOI":"10.1007\/s11263-023-01903-w","volume":"132","author":"Y Lan","year":"2022","unstructured":"Lan, Y., Loy, C.C., Dai, B.: DDF: correspondence distillation from nerf-based gan. IJCV 132, 611\u2013631 (2022)","journal-title":"IJCV"},{"key":"7_CR43","doi-asserted-by":"crossref","unstructured":"Lan, Y., Meng, X., Yang, S., Loy, C.C., Dai, B.: E3dge: self-supervised geometry-aware encoder for style-based 3D gan inversion. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02006"},{"key":"7_CR44","unstructured":"Lan, Y., et al.: Gaussian3Diff: 3D gaussian diffusion for 3D full head synthesis and editing. arXiv (2023)"},{"key":"7_CR45","doi-asserted-by":"crossref","unstructured":"Liu, R., Wu, R., Hoorick, B.V., Tokmakov, P., Zakharov, S., Vondrick, C.: Zero-1-to-3: zero-shot one image to 3D object (2023)","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"7_CR46","doi-asserted-by":"crossref","unstructured":"Long, X., et\u00a0al.: Wonder3d: single image to 3d using cross-domain diffusion. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00951"},{"key":"7_CR47","unstructured":"Lucas, J., Tucker, G., Grosse, R.B., Norouzi, M.: Understanding posterior collapse in generative latent variable models. In: ICLR (2019)"},{"key":"7_CR48","doi-asserted-by":"crossref","unstructured":"Meng, C., Gao, R., Kingma, D.P., Ermon, S., Ho, J., Salimans, T.: On distillation of guided diffusion models. In: CVPR, pp. 14297\u201314306 (2022)","DOI":"10.1109\/CVPR52729.2023.01374"},{"key":"7_CR49","doi-asserted-by":"crossref","unstructured":"Mescheder, L., Oechsle, M., Niemeyer, M., Nowozin, S., Geiger, A.: Occupancy networks: learning 3D reconstruction in function space. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00459"},{"key":"7_CR50","unstructured":"Mi, L., Kundu, A., Ross, D., Dellaert, F., Snavely, N., Fathi, A.: im2nerf: image to neural radiance field in the wild. arXiv (2022)"},{"key":"7_CR51","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":"7_CR52","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 (2023)","DOI":"10.1109\/CVPR52729.2023.00421"},{"key":"7_CR53","doi-asserted-by":"crossref","unstructured":"Nguyen-Phuoc, T., Li, C., Theis, L., Richardt, C., Yang, Y.: HoloGAN: unsupervised learning of 3D representations from natural images. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00768"},{"key":"7_CR54","unstructured":"Nichol, A., Jun, H., Dhariwal, P., Mishkin, P., Chen, M.: Point-e: a system for generating 3d point clouds from complex prompts (2022)"},{"key":"7_CR55","doi-asserted-by":"crossref","unstructured":"Niemeyer, M., Geiger, A.: GIRAFFE: representing scenes as compositional generative neural feature fields. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01129"},{"key":"7_CR56","unstructured":"Oquab, M., et al.: DINOv2: learning robust visual features without supervision (2023)"},{"key":"7_CR57","doi-asserted-by":"crossref","unstructured":"Or-El, R., Luo, X., Shan, M., Shechtman, E., Park, J.J., Kemelmacher-Shlizerman, I.: StyleSDF: high-resolution 3D-consistent image and geometry generation. In: CVPR (2021)","DOI":"10.1109\/CVPR52688.2022.01314"},{"key":"7_CR58","unstructured":"Pan, X., Dai, B., Liu, Z., Loy, C.C., Luo, P.: Do 2D GANs know 3D shape? unsupervised 3D Shape Reconstruction from 2D Image GANs. In: ICLR (2021)"},{"key":"7_CR59","doi-asserted-by":"crossref","unstructured":"Park, J.J., Florence, P., Straub, J., Newcombe, R., Lovegrove, S.: Deepsdf: learning continuous signed distance functions for shape representation. In: CVPR, pp. 165\u2013174 (2019)","DOI":"10.1109\/CVPR.2019.00025"},{"key":"7_CR60","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"7_CR61","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"523","DOI":"10.1007\/978-3-030-58580-8_31","volume-title":"Computer Vision \u2013 ECCV 2020","author":"S Peng","year":"2020","unstructured":"Peng, S., Niemeyer, M., Mescheder, L., Pollefeys, M., Geiger, A.: Convolutional occupancy networks. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12348, pp. 523\u2013540. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58580-8_31"},{"key":"7_CR62","unstructured":"Podell, D., et al.: SDXL: improving latent diffusion models for high-resolution image synthesis. arXiv (2023)"},{"key":"7_CR63","unstructured":"Poole, B., Jain, A., Barron, J.T., Mildenhall, B.: DreamFusion: text-to-3D using 2D diffusion. In: ICLR (2022)"},{"key":"7_CR64","unstructured":"Qi, C., Su, H., Mo, K., Guibas, L.: PointNet: deep learning on point sets for 3D classification and segmentation. arXiv (2016)"},{"key":"7_CR65","doi-asserted-by":"crossref","unstructured":"Qiu, L., et al.: Richdreamer: a generalizable normal-depth diffusion model for detail richness in text-to-3d. arXiv preprint arXiv:2311.16918 (2023)","DOI":"10.1109\/CVPR52733.2024.00946"},{"key":"7_CR66","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"7_CR67","doi-asserted-by":"crossref","unstructured":"Rebain, D., Matthews, M., Yi, K.M., Lagun, D., Tagliasacchi, A.: LOLNeRF: learn from one look. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00161"},{"key":"7_CR68","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 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"7_CR69","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"7_CR70","doi-asserted-by":"crossref","unstructured":"Sajjadi, M.S.M., et al.: Scene representation transformer: geometry-free novel view synthesis through set-latent scene representations. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00613"},{"key":"7_CR71","doi-asserted-by":"crossref","unstructured":"Sargent, K., et al.: VQ3D: learning a 3D-aware generative model on imagenet. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00391"},{"key":"7_CR72","unstructured":"Schuhmann, C., et al.: LAION-5B: an open large-scale dataset for training next generation image-text models. arXiv (2022)"},{"key":"7_CR73","unstructured":"Schwarz, K., Liao, Y., Niemeyer, M., Geiger, A.: GRAF: generative radiance fields for 3D-aware image synthesis. In: NeurIPS (2020)"},{"key":"7_CR74","unstructured":"Shi, R., et al.: Zero123++: a single image to consistent multi-view diffusion base model. arXiv (2023)"},{"key":"7_CR75","doi-asserted-by":"crossref","unstructured":"Shue, J., Chan, E., Po, R., Ankner, Z., Wu, J., Wetzstein, G.: 3d neural field generation using triplane diffusion. In: CVPR (2022)","DOI":"10.1109\/CVPR52729.2023.02000"},{"key":"7_CR76","unstructured":"Sitzmann, V., Rezchikov, S., Freeman, W.T., Tenenbaum, J.B., Durand, F.: Light field networks: neural scene representations with single-evaluation rendering. In: NeurIPS (2021)"},{"key":"7_CR77","unstructured":"Sitzmann, V., Zollh\u00f6fer, M., Wetzstein, G.: Scene representation networks: continuous 3D-structure-aware neural scene representations. In: NeurIPS (2019)"},{"key":"7_CR78","unstructured":"Song, Y., Sohl-Dickstein, J., Kingma, D.P., Kumar, A., Ermon, S., Poole, B.: Score-based generative modeling through stochastic differential equations. In: ICLR (2021)"},{"issue":"6","key":"7_CR79","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3550454.3555506","volume":"41","author":"J Sun","year":"2022","unstructured":"Sun, J., Wang, X., Shi, Y., Wang, L., Wang, J., Liu, Y.: Ide-3d: interactive disentangled editing for high-resolution 3D-aware portrait synthesis. ACM Trans. Graph. (TOG) 41(6), 1\u201310 (2022)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"7_CR80","doi-asserted-by":"crossref","unstructured":"Sun, J., et al.: FENeRF: face editing in neural radiance fields. arXiv (2021)","DOI":"10.1109\/CVPR52688.2022.00752"},{"key":"7_CR81","doi-asserted-by":"crossref","unstructured":"Szymanowicz, S., Rupprecht, C., Vedaldi, A.: Splatter image: ultra-fast single-view 3D reconstruction. arXiv (2023)","DOI":"10.1109\/CVPR52733.2024.00972"},{"key":"7_CR82","unstructured":"Tang, Z., et al.: Volumediffusion: flexible text-to-3d generation with efficient volumetric encoder (2023)"},{"key":"7_CR83","doi-asserted-by":"crossref","unstructured":"Tewari, A., et al.: Advances in neural rendering. Comput. Graph. Forum 41 (2021)","DOI":"10.1111\/cgf.14507"},{"key":"7_CR84","unstructured":"Tewari, A., et al.: Diffusion with forward models: solving stochastic inverse problems without direct supervision. In: NeurIPS (2023)"},{"key":"7_CR85","doi-asserted-by":"crossref","unstructured":"Thanh-Tung, H., Tran, T.: Catastrophic forgetting and mode collapse in gans. In: IJCNN, pp. 1\u201310 (2020)","DOI":"10.1109\/IJCNN48605.2020.9207181"},{"key":"7_CR86","doi-asserted-by":"crossref","unstructured":"Thomas, H., Qi, C.R., Deschaud, J.E., Marcotegui, B., Goulette, F., Guibas, L.J.: KPConv: flexible and deformable convolution for point clouds. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00651"},{"key":"7_CR87","unstructured":"Vahdat, A., Kreis, K., Kautz, J.: Score-based generative modeling in latent space. In: NeurIPS (2021)"},{"key":"7_CR88","doi-asserted-by":"crossref","unstructured":"Wang, Q., et al.: IBRNet: learning multi-view image-based rendering. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00466"},{"key":"7_CR89","doi-asserted-by":"crossref","unstructured":"Wang, T., et\u00a0al.: RODIN: a generative model for sculpting 3D digital avatars using diffusion. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00443"},{"key":"7_CR90","unstructured":"Wang, Z., Lu, C., Wang, Y., Bao, F., Li, C., Su, H., Zhu, J.: Prolificdreamer: high-fidelity and diverse text-to-3D generation with variational score distillation. In: NeurIPS (2023)"},{"key":"7_CR91","doi-asserted-by":"crossref","unstructured":"Weng, C.Y., Srinivasan, P.P., Curless, B., Kemelmacher-Shlizerman, I.: PersonNeRF: personalized reconstruction from photo collections. In: CVPR, pp. 524\u2013533 (2023)","DOI":"10.1109\/CVPR52729.2023.00058"},{"key":"7_CR92","doi-asserted-by":"crossref","unstructured":"Wu, C.Y., Johnson, J., Malik, J., Feichtenhofer, C., Gkioxari, G.: Multiview compressive coding for 3D reconstruction. arXiv preprint arXiv:2301.08247 (2023)","DOI":"10.1109\/CVPR52729.2023.00875"},{"key":"7_CR93","doi-asserted-by":"crossref","unstructured":"Xie, Y., et al.: Neural fields in visual computing and beyond. Comput. Graph. Forum 41 (2021)","DOI":"10.1111\/cgf.14505"},{"key":"7_CR94","unstructured":"Xu, Y., et al.: DMV3D: denoising multi-view diffusion using 3D large reconstruction model. In: ICLR (2024)"},{"key":"7_CR95","doi-asserted-by":"crossref","unstructured":"Yu, A., Ye, V., Tancik, M., Kanazawa, A.: PixelNeRF: neural radiance fields from one or few images. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00455"},{"key":"7_CR96","doi-asserted-by":"crossref","unstructured":"Yu, X., et al.: MVImgNet: a large-scale dataset of multi-view images. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00883"},{"key":"7_CR97","doi-asserted-by":"publisher","unstructured":"Zhang, B., Tang, J., Nie\u00dfner, M., Wonka, P.: 3DShape2VecSet: a 3d shape representation for neural fields and generative diffusion models. ACM Trans. Graph. 42(4) (2023). https:\/\/doi.org\/10.1145\/3592442","DOI":"10.1145\/3592442"},{"key":"7_CR98","unstructured":"Zhang, J., et al.: Deformtoon3d: deformable 3D toonification from neural radiance fields. In: ICCV (2023)"},{"key":"7_CR99","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"7_CR100","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 (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"7_CR101","doi-asserted-by":"crossref","unstructured":"Zhou, L., Du, Y., Wu, J.: 3D shape generation and completion through point-voxel diffusion. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00577"}],"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\/978-3-031-73235-5_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T21:16:41Z","timestamp":1732828601000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73235-5_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,30]]},"ISBN":["9783031732348","9783031732355"],"references-count":101,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73235-5_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,30]]},"assertion":[{"value":"30 September 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"}}]}}