{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T02:14:14Z","timestamp":1774404854845,"version":"3.50.1"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031730207","type":"print"},{"value":"9783031730214","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"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\/978-3-031-73021-4_1","type":"book-chapter","created":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T09:16:52Z","timestamp":1732094212000},"page":"1-18","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Score Distillation Sampling with\u00a0Learned Manifold Corrective"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9107-4173","authenticated-orcid":false,"given":"Thiemo","family":"Alldieck","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4885-4876","authenticated-orcid":false,"given":"Nikos","family":"Kolotouros","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5256-886X","authenticated-orcid":false,"given":"Cristian","family":"Sminchisescu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,21]]},"reference":[{"key":"1_CR1","unstructured":"Armandpour, M., Zheng, H., Sadeghian, A., Sadeghian, A., Zhou, M.: Re-imagine the negative prompt algorithm: transform 2D diffusion into 3D, alleviate Janus problem and beyond. arXiv preprint arXiv:2304.04968 (2023)"},{"key":"1_CR2","doi-asserted-by":"crossref","unstructured":"Brooks, T., Holynski, A., Efros, A.A.: InstructPix2Pix: learning to follow image editing instructions. In: IEEE Conference on Computer Vision and Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"1_CR3","doi-asserted-by":"crossref","unstructured":"Choi, Y., Uh, Y., Yoo, J., Ha, J.W.: StarGAN v2: diverse image synthesis for multiple domains. In: IEEE Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.00821"},{"key":"1_CR4","unstructured":"Chung, H., Kim, J., Mccann, M.T., Klasky, M.L., Ye, J.C.: Diffusion posterior sampling for general noisy inverse problems. In: International Conference on Learning Representation (2022)"},{"key":"1_CR5","first-page":"25683","volume":"35","author":"H Chung","year":"2022","unstructured":"Chung, H., Sim, B., Ryu, D., Ye, J.C.: Improving diffusion models for inverse problems using manifold constraints. Adv. Neural Inform. Process. Syst. 35, 25683\u201325696 (2022)","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"1_CR6","doi-asserted-by":"crossref","unstructured":"Croitoru, F.A., Hondru, V., Ionescu, R.T., Shah, M.: Diffusion models in vision: a survey. IEEE Trans. Pattern Anal. Mach. Intell. (2023)","DOI":"10.1109\/TPAMI.2023.3261988"},{"key":"1_CR7","doi-asserted-by":"crossref","unstructured":"Gao, S., et al.: Implicit diffusion models for continuous super-resolution. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10021\u201310030 (2023)","DOI":"10.1109\/CVPR52729.2023.00966"},{"key":"1_CR8","doi-asserted-by":"crossref","unstructured":"Hertz, A., Aberman, K., Cohen-Or, D.: Delta denoising score. In: International Conference on Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.00221"},{"key":"1_CR9","doi-asserted-by":"crossref","unstructured":"Hessel, J., Holtzman, A., Forbes, M., Bras, R.L., Choi, Y.: CLIPScore: a reference-free evaluation metric for image captioning. arXiv preprint arXiv:2104.08718 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"1_CR10","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural Inform. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"1_CR11","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. In: NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications (2021)"},{"key":"1_CR12","doi-asserted-by":"crossref","unstructured":"Jain, A., Xie, A., Abbeel, P.: VectorFusion: text-to-SVG by abstracting pixel-based diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1911\u20131920 (2023)","DOI":"10.1109\/CVPR52729.2023.00190"},{"key":"1_CR13","unstructured":"Katzir, O., Patashnik, O., Cohen-Or, D., Lischinski, D.: Noise-free score distillation. arXiv preprint arXiv:2310.17590 (2023)"},{"key":"1_CR14","unstructured":"Kawar, B., Elad, M., Ermon, S., Song, J.: Denoising diffusion restoration models. Adv. Neural Inform. Process. Syst. (2022)"},{"key":"1_CR15","doi-asserted-by":"crossref","unstructured":"Kawar, B., et al.: Imagic: text-based real image editing with diffusion models. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 6007\u20136017 (2023)","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"1_CR16","unstructured":"Kim, S., Lee, K., Choi, J.S., Jeong, J., Sohn, K., Shin, J.: Collaborative score distillation for consistent visual synthesis. arXiv preprint arXiv:2307.04787 (2023)"},{"key":"1_CR17","unstructured":"Kolotouros, N., Alldieck, T., Zanfir, A., Bazavan, E.G., Fieraru, M., Sminchisescu, C.: DreamHuman: animatable 3D avatars from text. Adv. Neural Inform. Process. Syst. (2023)"},{"key":"1_CR18","doi-asserted-by":"crossref","unstructured":"Kuznetsova, A., et al.: The open images dataset v4: unified image classification, object detection, and visual relationship detection at scale. Int. J. Comput. Vis. (2020)","DOI":"10.1007\/s11263-020-01316-z"},{"key":"1_CR19","unstructured":"Li, X., et al.: Diffusion models for image restoration and enhancement\u2013a comprehensive survey. arXiv preprint arXiv:2308.09388 (2023)"},{"key":"1_CR20","doi-asserted-by":"crossref","unstructured":"Lin, C.H., et al.: Magic3D: high-resolution text-to-3D content creation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 300\u2013309 (2023)","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"1_CR21","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":"1_CR22","unstructured":"Liu, Q., Wang, D.: Stein variational gradient descent: a general purpose Bayesian inference algorithm. Adv. Neural Inf. Process. Syst. 29 (2016)"},{"key":"1_CR23","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: International Conference on Computer Vision, pp. 9298\u20139309 (2023)","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"1_CR24","doi-asserted-by":"crossref","unstructured":"Lugmayr, A., Danelljan, M., Romero, A., Yu, F., Timofte, R., Van\u00a0Gool, L.: Repaint: inpainting using denoising diffusion probabilistic models. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 11461\u201311471 (2022)","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"1_CR25","unstructured":"Meng, C., et al.: SDEdit: guided image synthesis and editing with stochastic differential equations. In: International Conference on Learning Representation (2022)"},{"key":"1_CR26","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: IEEE Conference on Computer Vision and Pattern Recognition, pp. 12663\u201312673 (2023)","DOI":"10.1109\/CVPR52729.2023.01218"},{"key":"1_CR27","unstructured":"Nichol, A., et al.: GLIDE: towards photorealistic image generation and editing with text-guided diffusion models. In: International Conference on Machine Learning (2022)"},{"key":"1_CR28","unstructured":"Park, D.H., Azadi, S., Liu, X., Darrell, T., Rohrbach, A.: Benchmark for compositional text-to-image synthesis. In: Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 1) (2021)"},{"key":"1_CR29","unstructured":"Poole, B., Jain, A., Barron, J.T., Mildenhall, B.: DreamFusion: text-to-3D using 2D diffusion. In: International Conference on Learning Representation (2022)"},{"key":"1_CR30","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":"1_CR31","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"1_CR32","doi-asserted-by":"crossref","unstructured":"Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., Aberman, K.: DreamBooth: fine tuning text-to-image diffusion models for subject-driven generation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 22500\u201322510 (2023)","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"1_CR33","doi-asserted-by":"crossref","unstructured":"Saharia, C., et al.: Palette: image-to-image diffusion models. In: ACM SIGGRAPH 2022 Conference Proceedings, pp. 1\u201310 (2022)","DOI":"10.1145\/3528233.3530757"},{"key":"1_CR34","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 Inform. Process. Syst. 35, 36479\u201336494 (2022)","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"1_CR35","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":"1_CR36","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: International Conference on Learning Representation (2020)"},{"key":"1_CR37","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: IEEE Conference on Computer Vision and Pattern Recognition, pp. 12619\u201312629 (2023)","DOI":"10.1109\/CVPR52729.2023.01214"},{"key":"1_CR38","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":"1_CR39","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: IEEE Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"1_CR40","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"},{"key":"1_CR41","doi-asserted-by":"crossref","unstructured":"Zou, Z.X., Cheng, W., Cao, Y.P., Huang, S.S., Shan, Y., Zhang, S.H.: Sparse3D: distilling multiview-consistent diffusion for object reconstruction from sparse views. arXiv preprint arXiv:2308.14078 (2023)","DOI":"10.1609\/aaai.v38i7.28626"}],"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\/978-3-031-73021-4_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T09:40:45Z","timestamp":1732095645000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73021-4_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,21]]},"ISBN":["9783031730207","9783031730214"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73021-4_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,21]]},"assertion":[{"value":"21 November 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"}}]}}