{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T00:13:02Z","timestamp":1775779982098,"version":"3.50.1"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031727832","type":"print"},{"value":"9783031727849","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\/978-3-031-72784-9_8","type":"book-chapter","created":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T07:01:50Z","timestamp":1727593310000},"page":"136-152","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Learn to\u00a0Optimize Denoising Scores: A Unified and\u00a0Improved Diffusion Prior for\u00a03D Generation"],"prefix":"10.1007","author":[{"given":"Xiaofeng","family":"Yang","sequence":"first","affiliation":[]},{"given":"Yiwen","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Cheng","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Chi","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Yi","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Xulei","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Fayao","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Guosheng","family":"Lin","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,9,30]]},"reference":[{"key":"8_CR1","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":"8_CR2","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. In: Advances in Neural Information Processing Systems, vol. 34, pp. 8780\u20138794 (2021)"},{"key":"8_CR3","unstructured":"Gal, R., et al.: An image is worth one word: Personalizing text-to-image generation using textual inversion. arXiv preprint arXiv:2208.01618 (2022)"},{"key":"8_CR4","unstructured":"Graikos, A., Malkin, N., Jojic, N., Samaras, D.: Diffusion models as plug-and-play priors. In: Advances in Neural Information Processing Systems, vol. 35, pp. 14715\u201314728 (2022)"},{"key":"8_CR5","doi-asserted-by":"crossref","unstructured":"Haque, A., Tancik, M., Efros, A.A., Holynski, A., Kanazawa, A.: Instruct-NeRF2NeRF: editing 3D scenes with instructions. arXiv preprint arXiv:2303.12789 (2023)","DOI":"10.1109\/ICCV51070.2023.01808"},{"key":"8_CR6","unstructured":"He, Y., et al.: T3bench: benchmarking current progress in text-to-3D generation. arXiv preprint arXiv:2310.02977 (2023)"},{"key":"8_CR7","doi-asserted-by":"crossref","unstructured":"Hertz, A., Aberman, K., Cohen-Or, D.: Delta denoising score. arXiv preprint arXiv:2304.07090 (2023)","DOI":"10.1109\/ICCV51070.2023.00221"},{"key":"8_CR8","unstructured":"Hertz, A., Mokady, R., Tenenbaum, J., Aberman, K., Pritch, Y., Cohen-Or, D.: Prompt-to-prompt image editing with cross attention control. arXiv preprint arXiv:2208.01626 (2022)"},{"key":"8_CR9","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Advances in Neural Information Processing Systems, vol. 33, pp. 6840\u20136851 (2020)"},{"issue":"1","key":"8_CR10","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":"8_CR11","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. In: NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications (2022)"},{"key":"8_CR12","unstructured":"Hu, E.J., et al.: LoRA: low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)"},{"key":"8_CR13","doi-asserted-by":"crossref","unstructured":"Kawar, B., et al.: Imagic: text-based real image editing with diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6007\u20136017 (2023)","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"8_CR14","doi-asserted-by":"crossref","unstructured":"Kerbl, B., Kopanas, G., Leimk\u00fchler, T., Drettakis, G.: 3D Gaussian splatting for real-time radiance field rendering. ACM Trans. Graph. 42(4) (2023). https:\/\/repo-sam.inria.fr\/fungraph\/3d-gaussian-splatting\/","DOI":"10.1145\/3592433"},{"key":"8_CR15","unstructured":"Li, W., Chen, R., Chen, X., Tan, P.: SweetDreamer: aligning geometric priors in 2D diffusion for consistent text-to-3D. arXiv preprint arXiv:2310.02596 (2023)"},{"key":"8_CR16","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":"8_CR17","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":"8_CR18","doi-asserted-by":"crossref","unstructured":"Long, X., et\u00a0al.: Wonder3D: single image to 3D using cross-domain diffusion. arXiv preprint arXiv:2310.15008 (2023)","DOI":"10.1109\/CVPR52733.2024.00951"},{"key":"8_CR19","doi-asserted-by":"crossref","unstructured":"Melas-Kyriazi, L., Rupprecht, C., Laina, I., Vedaldi, A.: RealFusion: 360 reconstruction of any object from a single image. In: CVPR (2023). https:\/\/arxiv.org\/abs\/2302.10663","DOI":"10.1109\/CVPR52729.2023.00816"},{"key":"8_CR20","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"},{"issue":"1","key":"8_CR21","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":"8_CR22","doi-asserted-by":"crossref","unstructured":"Mokady, R., Hertz, A., Aberman, K., Pritch, Y., Cohen-Or, D.: Null-text inversion for editing real images using guided diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6038\u20136047 (2023)","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"8_CR23","doi-asserted-by":"crossref","unstructured":"Mou, C., et al.: T2I-Adapter: learning adapters to dig out more controllable ability for text-to-image diffusion models. arXiv preprint arXiv:2302.08453 (2023)","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"8_CR24","unstructured":"Nichol, A.Q., et al.: GLIDE: towards photorealistic image generation and editing with text-guided diffusion models. In: International Conference on Machine Learning, pp. 16784\u201316804. PMLR (2022)"},{"key":"8_CR25","unstructured":"Poole, B., Jain, A., Barron, J.T., Mildenhall, B.: DreamFusion: text-to-3D using 2D diffusion. arXiv (2022)"},{"key":"8_CR26","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":"8_CR27","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with CLIP latents. arXiv preprint arXiv:2204.06125 (2022)"},{"key":"8_CR28","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":"8_CR29","unstructured":"Saharia, C., et\u00a0al.: Photorealistic text-to-image diffusion models with deep language understanding. In: Advances in Neural Information Processing Systems (2022)"},{"key":"8_CR30","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":"8_CR31","unstructured":"Shi, R., et al.: Zero123++: a single image to consistent multi-view diffusion base model. arXiv preprint arXiv:2310.15110 (2023)"},{"key":"8_CR32","unstructured":"Shi, Y., Wang, P., Ye, J., Mai, L., Li, K., Yang, X.: MVDream: multi-view diffusion for 3D generation. arXiv:2308.16512 (2023)"},{"key":"8_CR33","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)"},{"key":"8_CR34","unstructured":"Song, Y., Ermon, S.: Generative modeling by estimating gradients of the data distribution. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"8_CR35","unstructured":"Song, Y., Ermon, S.: Improved techniques for training score-based generative models. In: Advances in Neural Information Processing Systems, vol. 33, pp. 12438\u201312448 (2020)"},{"key":"8_CR36","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":"8_CR37","unstructured":"Tang, S., Zhang, F., Chen, J., Wang, P., Furukawa, Y.: MVDiffusion: enabling holistic multi-view image generation with correspondence-aware diffusion. arXiv (2023)"},{"key":"8_CR38","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":"8_CR39","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":"8_CR40","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":"8_CR41","unstructured":"Xu, J., et al.: ImageReward: learning and evaluating human preferences for text-to-image generation (2023)"},{"key":"8_CR42","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":"8_CR43","unstructured":"Yu, L., Xiang, W., Han, K.: Edit-DiffNeRF: editing 3D neural radiance fields using 2D diffusion model. arXiv preprint arXiv:2306.09551 (2023)"},{"key":"8_CR44","unstructured":"Yu, X., Guo, Y.C., Li, Y., Liang, D., Zhang, S.H., Qi, X.: Text-to-3D with classifier score distillation. In: The Twelfth International Conference on Learning Representations (2024). https:\/\/openreview.net\/forum?id=ktG8Tun1Cy"},{"key":"8_CR45","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"}],"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\/978-3-031-72784-9_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T07:48:18Z","timestamp":1727596098000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72784-9_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,30]]},"ISBN":["9783031727832","9783031727849"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72784-9_8","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"}}]}}