{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:06:43Z","timestamp":1784268403637,"version":"3.55.0"},"publisher-location":"Cham","reference-count":53,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031732317","type":"print"},{"value":"9783031732324","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\/978-3-031-73232-4_21","type":"book-chapter","created":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T06:01:53Z","timestamp":1727589713000},"page":"370-386","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["ZeST: Zero-Shot Material Transfer from\u00a0a\u00a0Single Image"],"prefix":"10.1007","author":[{"given":"Ta-Ying","family":"Cheng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Prafull","family":"Sharma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew","family":"Markham","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Niki","family":"Trigoni","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Varun","family":"Jampani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,9,30]]},"reference":[{"key":"21_CR1","unstructured":"https:\/\/www.textures.com\/browse\/pbr-materials\/114558"},{"issue":"4","key":"21_CR2","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1145\/2461912.2461978","volume":"32","author":"M Aittala","year":"2013","unstructured":"Aittala, M., Weyrich, T., Lehtinen, J.: Practical SVBRDF capture in the frequency domain. ACM Trans. Graph. 32(4), 110\u2013111 (2013)","journal-title":"ACM Trans. Graph."},{"issue":"4","key":"21_CR3","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1145\/2766967","volume":"34","author":"M Aittala","year":"2015","unstructured":"Aittala, M., Weyrich, T., Lehtinen, J., et al.: Two-shot SVBRDF capture for stationary materials. ACM Trans. Graph. 34(4), 110\u2013111 (2015)","journal-title":"ACM Trans. Graph."},{"key":"21_CR4","unstructured":"Bar-Tal, O., Yariv, L., Lipman, Y., Dekel, T.: MultiDiffusion: fusing diffusion paths for controlled image generation (2023)"},{"key":"21_CR5","doi-asserted-by":"crossref","unstructured":"Bell, S., Upchurch, P., Snavely, N., Bala, K.: Material recognition in the wild with the materials in context database. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3479\u20133487 (2015)","DOI":"10.1109\/CVPR.2015.7298970"},{"key":"21_CR6","doi-asserted-by":"crossref","unstructured":"Bhat, S.F., Mitra, N.J., Wonka, P.: LooseControl: lifting controlnet for generalized depth conditioning. arXiv preprint arXiv:2312.03079 (2023)","DOI":"10.1145\/3641519.3657525"},{"key":"21_CR7","doi-asserted-by":"crossref","unstructured":"Brooks, T., Holynski, A., Efros, A.A.: InstructPix2Pix: learning to follow image editing instructions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18392\u201318402 (2023)","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"21_CR8","doi-asserted-by":"crossref","unstructured":"Cao, M., Wang, X., Qi, Z., Shan, Y., Qie, X., Zheng, Y.: MasaCtrl: tuning-free mutual self-attention control for consistent image synthesis and editing. arXiv preprint arXiv:2304.08465 (2023)","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"21_CR9","doi-asserted-by":"crossref","unstructured":"Cao, T., Kreis, K., Fidler, S., Sharp, N., Yin, K.: Texfusion: synthesizing 3D textures with text-guided image diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4169\u20134181 (2023)","DOI":"10.1109\/ICCV51070.2023.00385"},{"key":"21_CR10","doi-asserted-by":"crossref","unstructured":"Chen, D.Z., Siddiqui, Y., Lee, H.Y., Tulyakov, S., Nie\u00dfner, M.: Text2tex: text-driven texture synthesis via diffusion models. arXiv preprint arXiv:2303.11396 (2023)","DOI":"10.1109\/ICCV51070.2023.01701"},{"key":"21_CR11","doi-asserted-by":"crossref","unstructured":"Chen, M., Laina, I., Vedaldi, A.: Training-free layout control with cross-attention guidance. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 5343\u20135353 (2024)","DOI":"10.1109\/WACV57701.2024.00526"},{"key":"21_CR12","unstructured":"Chen, W., et al.: Subject-driven text-to-image generation via apprenticeship learning. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"21_CR13","doi-asserted-by":"crossref","unstructured":"Cheng, T.Y., et al.: Learning continuous 3D words for text-to-image generation. arXiv preprint arXiv:2402.08654 (2024)","DOI":"10.1109\/CVPR52733.2024.00645"},{"key":"21_CR14","doi-asserted-by":"crossref","unstructured":"Corneanu, C., Gadde, R., Martinez, A.M.: LatentPaint: image inpainting in latent space with diffusion models. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 4334\u20134343 (2024)","DOI":"10.1109\/WACV57701.2024.00428"},{"key":"21_CR15","doi-asserted-by":"crossref","unstructured":"Deitke, M., et al.: Objaverse: a universe of annotated 3d objects. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13142\u201313153 (2023)","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"21_CR16","doi-asserted-by":"crossref","unstructured":"Delanoy, J., Lagunas, M., Condor, J., Gutierrez, D., Masia, B.: A generative framework for image-based editing of material appearance using perceptual attributes. In: Computer Graphics Forum, vol.\u00a041, pp. 453\u2013464. Wiley Online Library (2022)","DOI":"10.1111\/cgf.14446"},{"key":"21_CR17","doi-asserted-by":"crossref","unstructured":"Deschaintre, V., Aittala, M., Durand, F., Drettakis, G., Bousseau, A.: Flexible SVBRDF capture with a multi-image deep network. In: Computer graphics forum, vol.\u00a038, pp. 1\u201313. Wiley Online Library (2019)","DOI":"10.1111\/cgf.13765"},{"key":"21_CR18","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":"21_CR19","unstructured":"Fu, S., et al.: DreamSim: learning new dimensions of human visual similarity using synthetic data. In: NeurIPS (2023)"},{"key":"21_CR20","doi-asserted-by":"crossref","unstructured":"Ge, S., Park, T., Zhu, J.Y., Huang, J.B.: Expressive text-to-image generation with rich text. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7545\u20137556 (2023)","DOI":"10.1109\/ICCV51070.2023.00694"},{"issue":"11","key":"21_CR21","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":"21_CR22","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":"21_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":"21_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":"21_CR25","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)"},{"key":"21_CR26","doi-asserted-by":"crossref","unstructured":"Kang, M., et al.: Scaling up GANs for text-to-image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10124\u201310134 (2023)","DOI":"10.1109\/CVPR52729.2023.00976"},{"key":"21_CR27","first-page":"26565","volume":"35","author":"T Karras","year":"2022","unstructured":"Karras, T., Aittala, M., Aila, T., Laine, S.: Elucidating the design space of diffusion-based generative models. Adv. Neural. Inf. Process. Syst. 35, 26565\u201326577 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"3","key":"21_CR28","doi-asserted-by":"publisher","first-page":"654","DOI":"10.1145\/1141911.1141937","volume":"25","author":"EA Khan","year":"2006","unstructured":"Khan, E.A., Reinhard, E., Fleming, R.W., B\u00fclthoff, H.H.: Image-based material editing. ACM Trans. Graph. (TOG) 25(3), 654\u2013663 (2006)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"21_CR29","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, pp. 1931\u20131941 (2023)","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"21_CR30","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: GLIGEN: open-set grounded text-to-image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22511\u201322521 (2023)","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"21_CR31","doi-asserted-by":"crossref","unstructured":"Liang, Y., Wakaki, R., Nobuhara, S., Nishino, K.: Multimodal material segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19800\u201319808 (2022)","DOI":"10.1109\/CVPR52688.2022.01918"},{"key":"21_CR32","doi-asserted-by":"crossref","unstructured":"Lopes, I., Pizzati, F., de\u00a0Charette, R.: Material palette: extraction of materials from a single image. arXiv preprint arXiv:2311.17060 (2023)","DOI":"10.1109\/CVPR52733.2024.00419"},{"key":"21_CR33","unstructured":"Michel, O., Bhattad, A., VanderBilt, E., Krishna, R., Kembhavi, A., Gupta, T.: Object 3DIT: language-guided 3D-aware image editing. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"21_CR34","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":"21_CR35","doi-asserted-by":"crossref","unstructured":"Pandey, K., Guerrero, P., Gadelha, M., Hold-Geoffroy, Y., Singh, K., Mitra, N.: Diffusion handles: enabling 3D edits for diffusion models by lifting activations to 3D. arXiv preprint arXiv:2312.02190 (2023)","DOI":"10.1109\/CVPR52733.2024.00735"},{"key":"21_CR36","unstructured":"Podell, D., et al.: SDXL: improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952 (2023)"},{"key":"21_CR37","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":"21_CR38","doi-asserted-by":"crossref","unstructured":"Ranftl, R., Bochkovskiy, A., Koltun, V.: Vision transformers for dense prediction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12179\u201312188 (2021)","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"21_CR39","doi-asserted-by":"crossref","unstructured":"Richardson, E., Metzer, G., Alaluf, Y., Giryes, R., Cohen-Or, D.: Texture: text-guided texturing of 3D shapes. arXiv preprint arXiv:2302.01721 (2023)","DOI":"10.1145\/3588432.3591503"},{"key":"21_CR40","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. arXiv preprint arXiv:2208.12242 (2022)","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"21_CR41","unstructured":"Sharma, P., et al.: Alchemist: parametric control of material properties with diffusion models. arXiv preprint arXiv:2312.02970 (2023)"},{"issue":"4","key":"21_CR42","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3592390","volume":"42","author":"P Sharma","year":"2023","unstructured":"Sharma, P., Philip, J., Gharbi, M., Freeman, B., Durand, F., Deschaintre, V.: Materialistic: selecting similar materials in images. ACM Trans. Graph. (TOG) 42(4), 1\u201314 (2023)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"21_CR43","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":"21_CR44","doi-asserted-by":"crossref","unstructured":"Subias, J.D., Lagunas, M.: In-the-wild material appearance editing using perceptual attributes. In: Computer Graphics Forum, vol.\u00a042, pp. 333\u2013345. Wiley Online Library (2023)","DOI":"10.1111\/cgf.14765"},{"key":"21_CR45","doi-asserted-by":"crossref","unstructured":"Upchurch, P., Niu, R.: A dense material segmentation dataset for indoor and outdoor scene parsing. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) European Conference on Computer Vision, vol. 13668, pp. 450\u2013466. Springer, Cham (2022)","DOI":"10.1007\/978-3-031-20074-8_26"},{"key":"21_CR46","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":"21_CR47","doi-asserted-by":"crossref","unstructured":"Wang, X., Darrell, T., Rambhatla, S.S., Girdhar, R., Misra, I.: InstanceDiffusion: instance-level control for image generation. arXiv preprint arXiv:2402.03290 (2024)","DOI":"10.1109\/CVPR52733.2024.00596"},{"key":"21_CR48","doi-asserted-by":"crossref","unstructured":"Yang, Z., et\u00a0al.: ReCo: region-controlled text-to-image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14246\u201314255 (2023)","DOI":"10.1109\/CVPR52729.2023.01369"},{"key":"21_CR49","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":"21_CR50","doi-asserted-by":"crossref","unstructured":"Yeh, Y.Y., et\u00a0al.: TextureDreamer: image-guided texture synthesis through geometry-aware diffusion. arXiv preprint arXiv:2401.09416 (2024)","DOI":"10.1109\/CVPR52733.2024.00412"},{"key":"21_CR51","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":"21_CR52","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"},{"key":"21_CR53","unstructured":"Zhao, S., et al.: Uni-ControlNet: all-in-one control to text-to-image diffusion models. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"}],"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\/978-3-031-73232-4_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T06:07:59Z","timestamp":1727590079000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73232-4_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,30]]},"ISBN":["9783031732317","9783031732324"],"references-count":53,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73232-4_21","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"}}]}}