{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T11:10:52Z","timestamp":1789125052657,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":55,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370150","type":"print"},{"value":"9783032370167","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-37016-7_24","type":"book-chapter","created":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T10:55:12Z","timestamp":1789124112000},"page":"449-466","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DreamEdit3D: Personalization of\u00a0Multi-view Diffusion Models for\u00a03D Editing"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-0977-2378","authenticated-orcid":false,"given":"Jinxin","family":"Ai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6093-5199","authenticated-orcid":false,"given":"Matthias","family":"Nie\u00dfner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2656-3680","authenticated-orcid":false,"given":"Ziya","family":"Erko\u00e7","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,12]]},"reference":[{"key":"24_CR1","doi-asserted-by":"publisher","unstructured":"Avrahami, O., Aberman, K., Fried, O., Cohen-Or, D., Lischinski, D.: Break-a-scene: Extracting multiple concepts from a single image. In: SIGGRAPH Asia 2023 Conference Papers. SA \u201923, Association for Computing Machinery, New York, NY, USA (2023). https:\/\/doi.org\/10.1145\/3610548.3618154","DOI":"10.1145\/3610548.3618154"},{"key":"24_CR2","unstructured":"Baldridge, J., et al.: Imagen 3. arXiv preprint arXiv:2408.07009 (2024)"},{"key":"24_CR3","doi-asserted-by":"crossref","unstructured":"Barda, A., Gadelha, M., Kim, V.G., Aigerman, N., Bermano, A.H., Groueix, T.: Instant3dit: Multiview inpainting for fast editing of 3D objects (2024). https:\/\/arxiv.org\/abs\/2412.00518","DOI":"10.1109\/CVPR52734.2025.01517"},{"key":"24_CR4","unstructured":"Betker, J., et al.: Improving image generation with better captions (2023). https:\/\/cdn.openai.com\/papers\/dall-e-3.pdf, technical report, OpenAI"},{"key":"24_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":"24_CR6","unstructured":"Chen, H., et al.: Generic 3D diffusion adapter using controlled multi-view editing (2024)"},{"key":"24_CR7","doi-asserted-by":"crossref","unstructured":"Chen, M., et al.: Partgen: Part-level 3D generation and reconstruction with multi-view diffusion models (2024). https:\/\/arxiv.org\/abs\/2412.18608","DOI":"10.1109\/CVPR52734.2025.00552"},{"key":"24_CR8","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: Gaussianeditor: Swift and controllable 3D editing with gaussian splatting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21476\u201321485 (2024)","DOI":"10.1109\/CVPR52733.2024.02029"},{"key":"24_CR9","doi-asserted-by":"crossref","unstructured":"Erko\u00e7, Z., et al.: Preditor3d: Fast and precise 3D shape editing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 640\u2013649 (2025)","DOI":"10.1109\/CVPR52734.2025.00068"},{"key":"24_CR10","unstructured":"Esser, P., et al.: Scaling rectified flow transformers for high-resolution image synthesis (2024). https:\/\/arxiv.org\/abs\/2403.03206"},{"key":"24_CR11","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)"},{"issue":"4","key":"24_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3528223.3530164","volume":"41","author":"R Gal","year":"2022","unstructured":"Gal, R., Patashnik, O., Maron, H., Bermano, A.H., Chechik, G., Cohen-Or, D.: StyleGAN-NADA: CLIP-guided domain adaptation of image generators. ACM Trans. Graph. (TOG) 41(4), 1\u201313 (2022)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"24_CR13","doi-asserted-by":"crossref","unstructured":"Gao, R., et al.: Cat3d: Create anything in 3d with multi-view diffusion models (2024). https:\/\/arxiv.org\/abs\/2405.10314","DOI":"10.52202\/079017-2403"},{"key":"24_CR14","doi-asserted-by":"crossref","unstructured":"Goodfellow, I., et al.: Generative adversarial networks. Commun. ACM 63(11), 139\u2013144 (2020)","DOI":"10.1145\/3422622"},{"key":"24_CR15","doi-asserted-by":"crossref","unstructured":"Guo, Z., Wu, Y., Chen, Z., Chen, L., Zhang, P., He, Q.: Pulid: Pure and lightning id customization via contrastive alignment (2024). arxiv:2404.16022","DOI":"10.52202\/079017-1159"},{"key":"24_CR16","doi-asserted-by":"crossref","unstructured":"Haque, A., Tancik, M., Efros, A.A., Holynski, A., Kanazawa, A.: Instruct-nerf2nerf: Editing 3D scenes with instructions (2023). https:\/\/arxiv.org\/abs\/2303.12789","DOI":"10.1109\/ICCV51070.2023.01808"},{"key":"24_CR17","doi-asserted-by":"crossref","unstructured":"Haque, A., Tancik, M., Efros, A.A., Holynski, A., Kanazawa, A.: Instruct-nerf2nerf: Editing 3D scenes with instructions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 19740\u201319750 (2023)","DOI":"10.1109\/ICCV51070.2023.01808"},{"key":"24_CR18","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":"24_CR19","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)"},{"key":"24_CR20","unstructured":"Hong, Y., et al.: LRM: Large reconstruction model for single image to 3D. arXiv preprint arXiv:2311.04400 (2023)"},{"key":"24_CR21","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":"24_CR22","doi-asserted-by":"crossref","unstructured":"Kumari, N., Zhang, B., Zhang, R., Shechtman, E., Zhu, J.Y.: Multi-concept customization of text-to-image diffusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"24_CR23","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":"24_CR24","doi-asserted-by":"crossref","unstructured":"Liu, R., Wu, R., Van Hoorick, 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":"24_CR25","unstructured":"Liu, S., et\u00a0al.: Step1x-edit: A practical framework for general image editing. arXiv preprint arXiv:2504.17761 (2025)"},{"key":"24_CR26","unstructured":"Liu, Y., et al.: Syncdreamer: Generating multiview-consistent images from a single-view image. arXiv preprint arXiv:2309.03453 (2023)"},{"key":"24_CR27","doi-asserted-by":"crossref","unstructured":"Long, X., et al.: Wonder3D: Single image to 3D using cross-domain diffusion (2023). https:\/\/arxiv.org\/abs\/2310.15008","DOI":"10.1109\/CVPR52733.2024.00951"},{"key":"24_CR28","doi-asserted-by":"crossref","unstructured":"Lugmayr, A., Danelljan, M., Romero, A., Yu, F., Timofte, R., Van Gool, L.: RePaint: Inpainting using denoising diffusion probabilistic models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11461\u201311471 (2022)","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"24_CR29","unstructured":"Ma, Z., Chen, H., Yue, Y., Gkioxari, G.: Feedforward 3d editing via text-steerable image-to-3D. arXiv preprint arXiv:2512.13678 (2025)"},{"key":"24_CR30","doi-asserted-by":"crossref","unstructured":"Michel, O., Bar-On, R., Liu, R., Benaim, S., Hanocka, R.: Text2mesh: Text-driven neural stylization for meshes (2021). https:\/\/arxiv.org\/abs\/2112.03221","DOI":"10.1109\/CVPR52688.2022.01313"},{"key":"24_CR31","doi-asserted-by":"crossref","unstructured":"Mikaeili, A., Perel, O., Safaee, M., Cohen-Or, D., Mahdavi-Amiri, A.: Sked: Sketch-guided text-based 3d editing (2023). https:\/\/arxiv.org\/abs\/2303.10735","DOI":"10.1109\/ICCV51070.2023.01343"},{"key":"24_CR32","doi-asserted-by":"crossref","unstructured":"Ng, K.W., Zhu, X., Song, Y.Z., Xiang, T.: Partcraft: Crafting creative objects by parts (2024). https:\/\/arxiv.org\/abs\/2407.04604","DOI":"10.1007\/978-3-031-72673-6_23"},{"key":"24_CR33","unstructured":"Poole, B., Jain, A., Barron, J.T., Mildenhall, B.: Dreamfusion: Text-to-3D using 2D diffusion. arXiv preprint arXiv:2209.14988 (2022)"},{"key":"24_CR34","doi-asserted-by":"crossref","unstructured":"Raj, A., et al.: Dreambooth3d: Subject-driven text-to-3D generation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2349\u20132359 (2023)","DOI":"10.1109\/ICCV51070.2023.00223"},{"key":"24_CR35","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":"24_CR36","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":"24_CR37","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22500\u201322510 (2023)","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"24_CR38","doi-asserted-by":"crossref","unstructured":"Ruiz, N., et al.: Hyperdreambooth: Hypernetworks for fast personalization of text-to-image models (2024). https:\/\/arxiv.org\/abs\/2307.06949","DOI":"10.1109\/CVPR52733.2024.00624"},{"key":"24_CR39","doi-asserted-by":"crossref","unstructured":"Sella, E., Fiebelman, G., Hedman, P., Averbuch-Elor, H.: Vox-e: Text-guided voxel editing of 3D objects. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 430\u2013440 (2023)","DOI":"10.1109\/ICCV51070.2023.00046"},{"key":"24_CR40","unstructured":"Shah, V., et al.: Ziplora: Any subject in any style by effectively merging loras (2026). https:\/\/arxiv.org\/abs\/2311.13600"},{"key":"24_CR41","first-page":"6087","volume":"34","author":"T Shen","year":"2021","unstructured":"Shen, T., Gao, J., Yin, K., Liu, M.Y., Fidler, S.: Deep marching tetrahedra: a hybrid representation for high-resolution 3D shape synthesis. Adv. Neural. Inf. Process. Syst. 34, 6087\u20136101 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"24_CR42","unstructured":"Shi, Y., Wang, P., Ye, J., Long, M., Li, K., Yang, X.: Mvdream: Multi-view diffusion for 3D generation. arXiv preprint arXiv:2308.16512 (2023)"},{"key":"24_CR43","unstructured":"Voynov, A., Chu, Q., Cohen-Or, D., Aberman, K.: p+: Extended textual conditioning in text-to-image generation. arXiv preprint arXiv:2303.09522 (2023)"},{"key":"24_CR44","doi-asserted-by":"crossref","unstructured":"Wang, J., Fang, J., Zhang, X., Xie, L., Tian, Q.: Gaussianeditor: Editing 3D gaussians delicately with text instructions (2024). https:\/\/arxiv.org\/abs\/2311.16037","DOI":"10.1109\/CVPR52733.2024.01975"},{"key":"24_CR45","unstructured":"Wang, P., Shi, Y.: Imagedream: Image-prompt multi-view diffusion for 3D generation (2023). https:\/\/arxiv.org\/abs\/2312.02201"},{"key":"24_CR46","unstructured":"Wang, Q., et al.: Instantid: Zero-shot identity-preserving generation in seconds (2024). https:\/\/arxiv.org\/abs\/2401.07519"},{"key":"24_CR47","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: Prolificdreamer: High-fidelity and diverse text-to-3D generation with variational score distillation. Adv. Neural. Inf. Process. Syst. 36, 8406\u20138441 (2023)","DOI":"10.52202\/075280-0368"},{"key":"24_CR48","doi-asserted-by":"crossref","unstructured":"Wu, J., et al.: Gaussctrl: Multi-view consistent text-driven 3D gaussian splatting editing. In: European Conference on Computer Vision, pp. 55\u201371. Springer (2024)","DOI":"10.1007\/978-3-031-72630-9_4"},{"key":"24_CR49","doi-asserted-by":"crossref","unstructured":"Xiang, J., et al.: Structured 3D latents for scalable and versatile 3D generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21469\u201321480 (2025)","DOI":"10.1109\/CVPR52734.2025.02000"},{"key":"24_CR50","doi-asserted-by":"crossref","unstructured":"Yang, Y., et al.: Wonder3d++: Cross-domain diffusion for high-fidelity 3D generation from a single image. IEEE Trans. Pattern Anal. Mach. Intell. 48(2), 1674\u20131688 (Feb 2026)","DOI":"10.1109\/TPAMI.2025.3618675"},{"key":"24_CR51","unstructured":"Ye, H., Zhang, J., Liu, S., Han, X., Yang, W.: Ip-adapter: Text compatible image prompt adapter for text-to-image diffusion models. arXiv preprint arXiv:2308.06721 (2023)"},{"key":"24_CR52","unstructured":"Ye, J., et al.: Nano3D: A training-free approach for efficient 3D editing without masks. arXiv preprint arXiv:2510.15019 (2025)"},{"key":"24_CR53","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":"24_CR54","doi-asserted-by":"crossref","unstructured":"Zheng, Y., Huang, M., Chen, N., Mao, Z.: Pro3d-editor: a progressive-views perspective for consistent and precise 3D editing (2025). https:\/\/arxiv.org\/abs\/2506.00512","DOI":"10.52202\/085713-4326"},{"key":"24_CR55","unstructured":"Zhuang, P., et al.: GTR: Improving large 3D reconstruction models through geometry and texture refinement. arXiv preprint arXiv:2406.05649 (2024)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37016-7_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T10:55:26Z","timestamp":1789124126000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37016-7_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370150","9783032370167"],"references-count":55,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37016-7_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"12 September 2026","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":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}