{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T18:22:52Z","timestamp":1768414972631,"version":"3.49.0"},"publisher-location":"Cham","reference-count":76,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726293","type":"print"},{"value":"9783031726309","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T00:00:00Z","timestamp":1733356800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T00:00:00Z","timestamp":1733356800000},"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\/978-3-031-72630-9_27","type":"book-chapter","created":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T05:17:52Z","timestamp":1733289472000},"page":"465-483","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["RodinHD: High-Fidelity 3D Avatar Generation with\u00a0Diffusion Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3520-1091","authenticated-orcid":false,"given":"Bowen","family":"Zhang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1457-2328","authenticated-orcid":false,"given":"Yiji","family":"Cheng","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9400-9107","authenticated-orcid":false,"given":"Chunyu","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3952-2522","authenticated-orcid":false,"given":"Ting","family":"Zhang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7314-6567","authenticated-orcid":false,"given":"Jiaolong","family":"Yang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1534-4549","authenticated-orcid":false,"given":"Yansong","family":"Tang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6767-8105","authenticated-orcid":false,"given":"Feng","family":"Zhao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0588-9331","authenticated-orcid":false,"given":"Dong","family":"Chen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8349-8868","authenticated-orcid":false,"given":"Baining","family":"Guo","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,5]]},"reference":[{"key":"27_CR1","unstructured":"Achlioptas, P., Diamanti, O., Mitliagkas, I., Guibas, L.: Learning representations and generative models for 3D point clouds. In: International Conference on Machine Learning, pp. 40\u201349. PMLR (2018)"},{"key":"27_CR2","unstructured":"Bautista, M.A., et\u00a0al.: GAUDI: a neural architect for immersive 3d scene generation. arXiv preprint arXiv:2207.13751 (2022)"},{"issue":"1","key":"27_CR3","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1007\/BF00128525","volume":"1","author":"RC Bolles","year":"1987","unstructured":"Bolles, R.C., Baker, H.H., Marimont, D.H.: Epipolar-plane image analysis: An approach to determining structure from motion. Int. J. Comput. Vis. 1(1), 7\u201355 (1987). https:\/\/doi.org\/10.1007\/BF00128525","journal-title":"Int. J. Comput. Vis."},{"key":"27_CR4","unstructured":"Brock, A., Lim, T., Ritchie, J.M., Weston, N.: Generative and discriminative voxel modeling with convolutional neural networks. arXiv preprint arXiv:1608.04236 (2016)"},{"key":"27_CR5","doi-asserted-by":"crossref","unstructured":"Chan, E.R., et\u00a0al.: Efficient geometry-aware 3D generative adversarial networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16123\u201316133 (2022)","DOI":"10.1109\/CVPR52688.2022.01565"},{"key":"27_CR6","doi-asserted-by":"crossref","unstructured":"Chan, E.R., Monteiro, M., Kellnhofer, P., Wu, J., Wetzstein, G.: pi-GAN: periodic implicit generative adversarial networks for 3D-aware image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5799\u20135809 (2021)","DOI":"10.1109\/CVPR46437.2021.00574"},{"key":"27_CR7","doi-asserted-by":"crossref","unstructured":"Chen, H., et al.: Single-stage diffusion NeRF: a unified approach to 3D generation and reconstruction. arXiv preprint arXiv:2304.06714 (2023)","DOI":"10.1109\/ICCV51070.2023.00229"},{"key":"27_CR8","unstructured":"Chen, T.: On the importance of noise scheduling for diffusion models. arXiv preprint arXiv:2301.10972 (2023)"},{"key":"27_CR9","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":"27_CR10","unstructured":"Cheng, Y., et al.: Efficient text-guided 3D-aware portrait generation with score distillation sampling on distribution. arXiv preprint arXiv:2306.02083 (2023)"},{"key":"27_CR11","doi-asserted-by":"crossref","unstructured":"Dai, W., Chen, L.H., Wang, J., Liu, J., Dai, B., Tang, Y.: MotionLCM: real-time controllable motion generation via latent consistency model. arXiv preprint arXiv:2404.19759 (2024)","DOI":"10.1007\/978-3-031-72640-8_22"},{"key":"27_CR12","doi-asserted-by":"crossref","unstructured":"Deng, Y., Yang, J., Xiang, J., Tong, X.: GRAM: generative radiance manifolds for 3D-aware image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10673\u201310683 (2022)","DOI":"10.1109\/CVPR52688.2022.01041"},{"key":"27_CR13","first-page":"8780","volume":"34","author":"P Dhariwal","year":"2021","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. Adv. Neural. Inf. Process. Syst. 34, 8780\u20138794 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"27_CR14","unstructured":"Ding, Z., Zhang, M., Wu, J., Tu, Z.: Patched denoising diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2308.01316 (2023)"},{"key":"27_CR15","unstructured":"Gao, J., et al.: GET3D: a generative model of high quality 3D textured shapes learned from images. arXiv preprint arXiv:2209.11163 (2022)"},{"issue":"11","key":"27_CR16","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3422622","volume":"63","author":"I Goodfellow","year":"2020","unstructured":"Goodfellow, I., et al.: Generative adversarial networks. Commun. ACM 63(11), 139\u2013144 (2020)","journal-title":"Commun. ACM"},{"key":"27_CR17","unstructured":"Gu, J., Zhai, S., Zhang, Y., Bautista, M.A., Susskind, J.: f-DM: a multi-stage diffusion model via progressive signal transformation. arXiv preprint arXiv:2210.04955 (2022)"},{"key":"27_CR18","unstructured":"Gu, J., Zhai, S., Zhang, Y., Susskind, J., Jaitly, N.: Matryoshka diffusion models. arXiv preprint arXiv:2310.15111 (2023)"},{"key":"27_CR19","doi-asserted-by":"crossref","unstructured":"Gu, S., et al.: Vector quantized diffusion model for text-to-image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10696\u201310706 (2022),","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"27_CR20","unstructured":"Gupta, A., Xiong, W., Nie, Y., Jones, I., O\u011fuz, B.: 3DGen: triplane latent diffusion for textured mesh generation. arXiv preprint arXiv:2303.05371 (2023)"},{"key":"27_CR21","doi-asserted-by":"crossref","unstructured":"Hang, T., et al.: Efficient diffusion training via Min-SNR weighting strategy. arXiv preprint arXiv:2303.09556 (2023)","DOI":"10.1109\/ICCV51070.2023.00684"},{"key":"27_CR22","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: Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"27_CR23","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."},{"issue":"1","key":"27_CR24","first-page":"2249","volume":"23","author":"J Ho","year":"2022","unstructured":"Ho, J., Saharia, C., Chan, W., Fleet, D.J., Norouzi, M., Salimans, T.: Cascaded diffusion models for high fidelity image generation. J. Mach. Learn. Res. 23(1), 2249\u20132281 (2022)","journal-title":"J. Mach. Learn. Res."},{"key":"27_CR25","unstructured":"Hoogeboom, E., Heek, J., Salimans, T.: simple diffusion: end-to-end diffusion for high resolution images. arXiv preprint arXiv:2301.11093 (2023)"},{"key":"27_CR26","unstructured":"Hu, E.J., et al.: LoRA: low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)"},{"key":"27_CR27","unstructured":"Jabri, A., Fleet, D., Chen, T.: Scalable adaptive computation for iterative generation. arXiv preprint arXiv:2212.11972 (2022)"},{"key":"27_CR28","unstructured":"Jun, H., Nichol, A.: Shap-E: generating conditional 3D implicit functions. arXiv preprint arXiv:2305.02463 (2023)"},{"key":"27_CR29","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4401\u20134410 (2019)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"27_CR30","doi-asserted-by":"crossref","unstructured":"Kingma, D.P., Welling, M., et\u00a0al.: An introduction to variational autoencoders. Found. Trends\u00ae Mach. Learn. 12(4), 307\u2013392 (2019)","DOI":"10.1561\/2200000056"},{"issue":"13","key":"27_CR31","doi-asserted-by":"publisher","first-page":"3521","DOI":"10.1073\/pnas.1611835114","volume":"114","author":"J Kirkpatrick","year":"2017","unstructured":"Kirkpatrick, J., et al.: Overcoming catastrophic forgetting in neural networks. Proc. Natl. Acad. Sci. 114(13), 3521\u20133526 (2017)","journal-title":"Proc. Natl. Acad. Sci."},{"issue":"4","key":"27_CR32","first-page":"1","volume":"40","author":"R Li","year":"2021","unstructured":"Li, R., Li, X., Hui, K.H., Fu, C.W.: SP-GAN: sphere-guided 3D shape generation and manipulation. ACM Trans. Graph. (TOG) 40(4), 1\u201312 (2021)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"27_CR33","doi-asserted-by":"crossref","unstructured":"Li, Z., Tucker, R., Snavely, N., Holynski, A.: Generative image dynamics. arXiv preprint arXiv:2309.07906 (2023)","DOI":"10.1109\/CVPR52733.2024.02279"},{"key":"27_CR34","doi-asserted-by":"crossref","unstructured":"Liao, Y., Schwarz, K., Mescheder, L., Geiger, A.: Towards unsupervised learning of generative models for 3D controllable image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5871\u20135880 (2020)","DOI":"10.1109\/CVPR42600.2020.00591"},{"key":"27_CR35","doi-asserted-by":"crossref","unstructured":"Lin, C.H., et al.: Magic3D: high-resolution text-to-3D content creation. arXiv preprint arXiv:2211.10440 (2022)","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"27_CR36","doi-asserted-by":"crossref","unstructured":"Lin, S., Liu, B., Li, J., Yang, X.: Common diffusion noise schedules and sample steps are flawed. arXiv preprint arXiv:2305.08891 (2023)","DOI":"10.1109\/WACV57701.2024.00532"},{"key":"27_CR37","doi-asserted-by":"crossref","unstructured":"Liu, J., Dai, W., Wang, C., Cheng, Y., Tang, Y., Tong, X.: Plan, posture and go: towards open-world text-to-motion generation. arXiv preprint arXiv:2312.14828 (2023)","DOI":"10.1007\/978-3-031-73383-3_26"},{"key":"27_CR38","doi-asserted-by":"crossref","unstructured":"Ma, H., Zhang, L., Zhu, X., Zhang, J., Feng, J.: Accelerating score-based generative models for high-resolution image synthesis. arXiv preprint arXiv:2206.04029 (2022)","DOI":"10.1007\/978-3-031-20050-2_1"},{"issue":"1","key":"27_CR39","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":"27_CR40","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4328\u20134338 (2023)","DOI":"10.1109\/CVPR52729.2023.00421"},{"key":"27_CR41","unstructured":"Nichol, A., et al.: GLIDE: towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741 (2021)"},{"key":"27_CR42","unstructured":"Nichol, A.Q., Dhariwal, P.: Improved denoising diffusion probabilistic models. In: International Conference on Machine Learning, pp. 8162\u20138171. PMLR (2021)"},{"key":"27_CR43","doi-asserted-by":"crossref","unstructured":"Niemeyer, M., Geiger, A.: GIRAFFE: representing scenes as compositional generative neural feature fields. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11453\u201311464 (2021)","DOI":"10.1109\/CVPR46437.2021.01129"},{"key":"27_CR44","unstructured":"Ntavelis, E., Siarohin, A., Olszewski, K., Wang, C., Van\u00a0Gool, L., Tulyakov, S.: Autodecoding latent 3D diffusion models. arXiv preprint arXiv:2307.05445 (2023)"},{"key":"27_CR45","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 165\u2013174 (2019)","DOI":"10.1109\/CVPR.2019.00025"},{"key":"27_CR46","unstructured":"Podell, D., et al.: SDXL: improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952 (2023)"},{"key":"27_CR47","unstructured":"Poole, B., Jain, A., Barron, J.T., Mildenhall, B.: DreamFusion: text-to-3D using 2D diffusion. arXiv preprint arXiv:2209.14988 (2022)"},{"key":"27_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":"27_CR49","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":"27_CR50","unstructured":"Saharia, C., et\u00a0al.: Photorealistic text-to-image diffusion models with deep language understanding. arXiv preprint arXiv:2205.11487 (2022)"},{"key":"27_CR51","first-page":"20154","volume":"33","author":"K Schwarz","year":"2020","unstructured":"Schwarz, K., Liao, Y., Niemeyer, M., Geiger, A.: GRAF: generative radiance fields for 3D-aware image synthesis. Adv. Neural. Inf. Process. Syst. 33, 20154\u201320166 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"27_CR52","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20875\u201320886 (2023)","DOI":"10.1109\/CVPR52729.2023.02000"},{"key":"27_CR53","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"27_CR54","first-page":"7462","volume":"33","author":"V Sitzmann","year":"2020","unstructured":"Sitzmann, V., Martel, J., Bergman, A., Lindell, D., Wetzstein, G.: Implicit neural representations with periodic activation functions. Adv. Neural. Inf. Process. Syst. 33, 7462\u20137473 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"27_CR55","unstructured":"Song, Y., Sohl-Dickstein, J., Kingma, D.P., Kumar, A., Ermon, S., Poole, B.: Score-based generative modeling through stochastic differential equations. arXiv preprint arXiv:2011.13456 (2020)"},{"key":"27_CR56","unstructured":"Sun, J., et al.: DreamCraft3D: hierarchical 3D generation with bootstrapped diffusion prior. arXiv preprint arXiv:2310.16818 (2023)"},{"key":"27_CR57","unstructured":"Szab\u00f3, A., Meishvili, G., Favaro, P.: Unsupervised generative 3D shape learning from natural images. arXiv preprint arXiv:1910.00287 (2019)"},{"key":"27_CR58","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":"27_CR59","doi-asserted-by":"crossref","unstructured":"Tang, J., et al.: Make-It-Vivid: dressing your animatable biped cartoon characters from text. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6243\u20136253 (2024)","DOI":"10.1109\/CVPR52733.2024.00597"},{"key":"27_CR60","unstructured":"Tang, J., et al.: Explicitly controllable 3D-aware portrait generation. arXiv preprint arXiv:2209.05434 (2022)"},{"key":"27_CR61","doi-asserted-by":"crossref","unstructured":"Tang, Y., et al.: FLAG3D: a 3D fitness activity dataset with language instruction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22106\u201322117 (2023)","DOI":"10.1109\/CVPR52729.2023.02117"},{"key":"27_CR62","unstructured":"Teng, J., et al.: Relay diffusion: unifying diffusion process across resolutions for image synthesis. arXiv preprint arXiv:2309.03350 (2023)"},{"key":"27_CR63","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"27_CR64","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":"27_CR65","doi-asserted-by":"crossref","unstructured":"Wang, T., et\u00a0al.: RODIN: a generative model for sculpting 3D digital avatars using diffusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4563\u20134573 (2023)","DOI":"10.1109\/CVPR52729.2023.00443"},{"key":"27_CR66","doi-asserted-by":"crossref","unstructured":"Wang, X., Li, Y., Zhang, H., Shan, Y.: Towards real-world blind face restoration with generative facial prior. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9168\u20139178 (2021)","DOI":"10.1109\/CVPR46437.2021.00905"},{"key":"27_CR67","doi-asserted-by":"crossref","unstructured":"Wood, E., Baltru\u0161aitis, T., Hewitt, C., Dziadzio, S., Cashman, T.J., Shotton, J.: Fake it till you make it: face analysis in the wild using synthetic data alone. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3681\u20133691 (2021)","DOI":"10.1109\/ICCV48922.2021.00366"},{"key":"27_CR68","unstructured":"Wu, J., Zhang, C., Xue, T., Freeman, B., Tenenbaum, J.: Learning a probabilistic latent space of object shapes via 3D generative-adversarial modeling. In: Advances in Neural Information Processing Systems, vol. 29 (2016)"},{"issue":"4","key":"27_CR69","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3626193","volume":"56","author":"W Xia","year":"2023","unstructured":"Xia, W., Xue, J.H.: A survey on deep generative 3D-aware image synthesis. ACM Comput. Surv. 56(4), 1\u201334 (2023)","journal-title":"ACM Comput. Surv."},{"key":"27_CR70","doi-asserted-by":"crossref","unstructured":"Xiang, J., Yang, J., Deng, Y., Tong, X.: GRAM-HD: 3D-consistent image generation at high resolution with generative radiance manifolds. arXiv preprint arXiv:2206.07255 (2022)","DOI":"10.1109\/ICCV51070.2023.00209"},{"key":"27_CR71","doi-asserted-by":"crossref","unstructured":"Yin, F., et\u00a0al.: 3D GAN inversion with facial symmetry prior. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 342\u2013351 (2023)","DOI":"10.1109\/CVPR52729.2023.00041"},{"key":"27_CR72","unstructured":"Zeng, X., et al.: LION: latent point diffusion models for 3d shape generation. arXiv preprint arXiv:2210.06978 (2022)"},{"key":"27_CR73","unstructured":"Zhang, B., et al.: GaussianCube: structuring gaussian splatting using optimal transport for 3D generative modeling. arXiv preprint arXiv:2403.19655 (2024)"},{"key":"27_CR74","doi-asserted-by":"crossref","unstructured":"Zhang, B., et al.: StyleSwin: transformer-based GAN for high-resolution image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11304\u201311314 (2022)","DOI":"10.1109\/CVPR52688.2022.01102"},{"key":"27_CR75","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3836\u20133847 (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"27_CR76","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 586\u2013595 (2018)","DOI":"10.1109\/CVPR.2018.00068"}],"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\/978-3-031-72630-9_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T06:38:53Z","timestamp":1768199933000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72630-9_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,5]]},"ISBN":["9783031726293","9783031726309"],"references-count":76,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72630-9_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,5]]},"assertion":[{"value":"5 December 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"}}]}}