{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:33:25Z","timestamp":1778081605126,"version":"3.51.4"},"publisher-location":"Cham","reference-count":58,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726668","type":"print"},{"value":"9783031726675","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T00:00:00Z","timestamp":1727568000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T00:00:00Z","timestamp":1727568000000},"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\/978-3-031-72667-5_26","type":"book-chapter","created":{"date-parts":[[2024,9,28]],"date-time":"2024-09-28T20:11:48Z","timestamp":1727554308000},"page":"456-472","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["ColorPeel: Color Prompt Learning with\u00a0Diffusion Models via\u00a0Color and\u00a0Shape Disentanglement"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4799-6488","authenticated-orcid":false,"given":"Muhammad Atif","family":"Butt","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9605-8279","authenticated-orcid":false,"given":"Kai","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0414-7096","authenticated-orcid":false,"given":"Javier","family":"Vazquez-Corral","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9656-9706","authenticated-orcid":false,"given":"Joost","family":"van de Weijer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,29]]},"reference":[{"key":"26_CR1","doi-asserted-by":"crossref","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 (2023)","DOI":"10.1145\/3610548.3618154"},{"key":"26_CR2","unstructured":"Basu, S., et al.: Editval: benchmarking diffusion based text-guided image editing methods. arXiv preprint arXiv:2310.02426 (2023)"},{"key":"26_CR3","unstructured":"Berlin, B., Kay, P.: Basic color terms: their universality and evolution. University of California Press (1991)"},{"key":"26_CR4","doi-asserted-by":"crossref","unstructured":"Brooks, T., Holynski, A., Efros, A.A.: Instructpix2pix: learning to follow image editing instructions. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"26_CR5","unstructured":"Chang, H., et\u00a0al.: Muse: text-to-image generation via masked generative transformers. In: ICML (2023)"},{"key":"26_CR6","doi-asserted-by":"crossref","unstructured":"Chen, S., Huang, J.: FEC: three finetuning-free methods to enhance consistency for real image editing. arXiv preprint arXiv:2309.14934 (2023)","DOI":"10.1109\/ICICML60161.2023.10424833"},{"key":"26_CR7","unstructured":"Chen, W., et al.: Subject-driven text-to-image generation via apprenticeship learning. arXiv preprint arXiv:2304.00186 (2023)"},{"key":"26_CR8","unstructured":"Couairon, G., Verbeek, J., Schwenk, H., Cord, M.: Diffedit: diffusion-based semantic image editing with mask guidance. In: The Eleventh International Conference on Learning Representations (2023). https:\/\/openreview.net\/forum?id=3lge0p5o-M-"},{"key":"26_CR9","unstructured":"Daras, G., Dimakis, A.: Multiresolution textual inversion. In: NeurIPS 2022 Workshop on Score-Based Methods (2022)"},{"key":"26_CR10","unstructured":"Dong, Z., Wei, P., Lin, L.: Dreamartist: towards controllable one-shot text-to-image generation via contrastive prompt-tuning. arXiv preprint arXiv:2211.11337 (2022)"},{"key":"26_CR11","doi-asserted-by":"crossref","unstructured":"Gafni, O., Polyak, A., Ashual, O., Sheynin, S., Parikh, D., Taigman, Y.: Make-a-scene: scene-based text-to-image generation with human priors. In: ECCV, pp. 89\u2013106. Springer (2022)","DOI":"10.1007\/978-3-031-19784-0_6"},{"key":"26_CR12","unstructured":"Gal, R., et al.: An image is worth one word: personalizing text-to-image generation using textual inversion. In: ICLR (2023)"},{"key":"26_CR13","doi-asserted-by":"crossref","unstructured":"Gal, R., Arar, M., Atzmon, Y., Bermano, A.H., Chechik, G., Cohen-Or, D.: Designing an encoder for fast personalization of text-to-image models. arXiv preprint arXiv:2302.12228 (2023)","DOI":"10.1145\/3592133"},{"key":"26_CR14","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"},{"key":"26_CR15","unstructured":"Han, I., Yang, S., Kwon, T., Ye, J.C.: Highly personalized text embedding for image manipulation by stable diffusion. arXiv preprint arXiv:2303.08767 (2023)"},{"key":"26_CR16","doi-asserted-by":"crossref","unstructured":"Han, L., Li, Y., Zhang, H., Milanfar, P., Metaxas, D., Yang, F.: Svdiff: compact parameter space for diffusion fine-tuning. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00673"},{"key":"26_CR17","unstructured":"Han, L., et\u00a0al.: Improving negative-prompt inversion via proximal guidance. arXiv preprint arXiv:2306.05414 (2023)"},{"key":"26_CR18","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":"26_CR19","unstructured":"Hertz, A., Mokady, R., Tenenbaum, J., Aberman, K., Pritch, Y., Cohen-Or, D.: Prompt-to-prompt image editing with cross attention control. In: ICLR (2023)"},{"key":"26_CR20","unstructured":"Ho, J., et\u00a0al.: Imagen video: high definition video generation with diffusion models. arXiv preprint arXiv:2210.02303 (2022)"},{"key":"26_CR21","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. In: NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications (2022)"},{"key":"26_CR22","doi-asserted-by":"crossref","unstructured":"Hong, S., Lee, G., Jang, W., Kim, S.: Improving sample quality of diffusion models using self-attention guidance. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00686"},{"key":"26_CR23","unstructured":"Huang, Y., et al.: Diffusion model-based image editing: a survey. arXiv preprint arXiv:2402.17525 (2024)"},{"key":"26_CR24","unstructured":"Ju, X., Zeng, A., Bian, Y., Liu, S., Xu, Q.: Direct inversion: boosting diffusion-based editing with 3 lines of code. arXiv preprint arXiv:2310.01506 (2023)"},{"key":"26_CR25","doi-asserted-by":"crossref","unstructured":"Kawar, B., et al.: Imagic: text-based real image editing with diffusion models. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"26_CR26","unstructured":"Kirillov, A., et\u00a0al.: Segment anything. arXiv preprint arXiv:2304.02643 (2023)"},{"key":"26_CR27","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: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"26_CR28","unstructured":"Li, S., et al.: Stylediffusion: Prompt-Embedding Inversion for Text-Based Editing (2023)"},{"key":"26_CR29","unstructured":"Liu, Z., et al.: Cones: concept neurons in diffusion models for customized generation. In: ICML (2023)"},{"key":"26_CR30","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":"26_CR31","unstructured":"Meng, C., et al.: SDEdit: guided image synthesis and editing with stochastic differential equations. In: International Conference on Learning Representations (2022). https:\/\/openreview.net\/forum?id=aBsCjcPu_tE"},{"key":"26_CR32","unstructured":"Miyake, D., Iohara, A., Saito, Y., Tanaka, T.: Negative-prompt inversion: fast image inversion for editing with text-guided diffusion models. arXiv preprint arXiv:2305.16807 (2023)"},{"key":"26_CR33","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: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"26_CR34","doi-asserted-by":"crossref","unstructured":"Montag, E.D.: Empirical formula for creating error bars for the method of paired comparison. J. Elec. Imag. 15(1), 010502 (2006)","DOI":"10.1117\/1.2181547"},{"key":"26_CR35","doi-asserted-by":"crossref","unstructured":"Motamed, S., Paudel, D.P., Van\u00a0Gool, L.: Lego: learning to disentangle and invert concepts beyond object appearance in text-to-image diffusion models. arXiv preprint arXiv:2311.13833 (2023)","DOI":"10.1007\/978-3-031-72633-0_7"},{"key":"26_CR36","doi-asserted-by":"crossref","unstructured":"Parmar, G., Singh, K.K., Zhang, R., Li, Y., Lu, J., Zhu, J.Y.: Zero-shot image-to-image translation. In: Proceedings of the ACM SIGGRAPH Conference on Computer Graphics (2023)","DOI":"10.1145\/3588432.3591513"},{"key":"26_CR37","unstructured":"Podell, D., et al.: Sdxl: improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952 (2023)"},{"key":"26_CR38","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":"26_CR39","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: International Conference on Machine Learning, pp. 8821\u20138831. PMLR (2021)"},{"key":"26_CR40","unstructured":"Rassin, R., Hirsch, E., Glickman, D., Ravfogel, S., Goldberg, Y., Chechik, G.: Linguistic binding in diffusion models: enhancing attribute correspondence through attention map alignment. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"26_CR41","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 (CVPR), pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"26_CR42","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: MICCAI 2015, Part III 18, pp. 234\u2013241. Springer (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"26_CR43","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: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"26_CR44","unstructured":"Saharia, C., et\u00a0al.: Photorealistic text-to-image diffusion models with deep language understanding. Adv. Neural Inf. Process. Syst. (2022)"},{"key":"26_CR45","doi-asserted-by":"crossref","unstructured":"Shi, J., Xiong, W., Lin, Z., Jung, H.J.: Instantbooth: personalized text-to-image generation without test-time finetuning. arXiv preprint arXiv:2304.03411 (2023)","DOI":"10.1109\/CVPR52733.2024.00816"},{"key":"26_CR46","unstructured":"Shonenkov, A., Konstantinov, M., Bakshandaeva, D., Schuhmann, C., Ivanova, K., Klokova, N.: Deepfloyd-if (2023). https:\/\/github.com\/deep-floyd\/IF"},{"issue":"6","key":"26_CR47","doi-asserted-by":"publisher","first-page":"783","DOI":"10.1108\/00251740610673332","volume":"44","author":"S Singh","year":"2006","unstructured":"Singh, S.: Impact of color on marketing. Manag. Decis. 44(6), 783\u2013789 (2006)","journal-title":"Manag. Decis."},{"key":"26_CR48","doi-asserted-by":"crossref","unstructured":"Tang, C., Wang, K., van\u00a0de Weijer, J.: Iterinv: iterative inversion for pixel-level t2i models. In: Neurips 2023 Workshop on Diffusion Models (2023)","DOI":"10.1109\/ICME57554.2024.10687547"},{"key":"26_CR49","unstructured":"Tang, C., Wang, K., Yang, F., van\u00a0de Weijer, J.: Locinv: l-aware inversion for text-guided image editing. In: CVPR 2024 AI4CC Workshops (2024)"},{"key":"26_CR50","doi-asserted-by":"crossref","unstructured":"Thurstone, L.L.: A law of comparative judgment. In: Scaling, pp. 81\u201392. Routledge (1927)","DOI":"10.4324\/9781315128948-7"},{"key":"26_CR51","doi-asserted-by":"crossref","unstructured":"Tumanyan, N., Geyer, M., Bagon, S., Dekel, T.: Plug-and-play diffusion features for text-driven image-to-image translation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"26_CR52","doi-asserted-by":"crossref","unstructured":"Van De Weijer, J., Schmid, C., Verbeek, J., Larlus, D.: Learning color names for real-world applications. IEEE TIP 18(7), 1512\u20131523 (2009)","DOI":"10.1109\/TIP.2009.2019809"},{"key":"26_CR53","doi-asserted-by":"crossref","unstructured":"Vinker, Y., Voynov, A., Cohen-Or, D., Shamir, A.: Concept decomposition for visual exploration and inspiration. In: SIGGRAPH Asia 2023 (2023)","DOI":"10.1145\/3618315"},{"key":"26_CR54","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":"26_CR55","unstructured":"Wang, K., Yang, F., Yang, S., Butt, M.A., van\u00a0de Weijer, J.: Dynamic prompt learning: addressing cross-attention leakage for text-based image editing. Adv. Neural Inf. Process. Syst. (2023)"},{"key":"26_CR56","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":"26_CR57","unstructured":"Zhang, S., Xiao, S., Huang, W.: Forgedit: text guided image editing via learning and forgetting. arXiv preprint arXiv:2309.10556 (2023)"},{"key":"26_CR58","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Han, L., Ghosh, A., Metaxas, D., Ren, J.: Sine: single image editing with text-to-image diffusion models. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00584"}],"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\/978-3-031-72667-5_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T21:09:24Z","timestamp":1732828164000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72667-5_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,29]]},"ISBN":["9783031726668","9783031726675"],"references-count":58,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72667-5_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,29]]},"assertion":[{"value":"29 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"}}]}}