{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T17:46:50Z","timestamp":1772905610026,"version":"3.50.1"},"publisher-location":"Cham","reference-count":72,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726729","type":"print"},{"value":"9783031726736","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T00:00:00Z","timestamp":1729555200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T00:00:00Z","timestamp":1729555200000},"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\/978-3-031-72673-6_23","type":"book-chapter","created":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T16:03:50Z","timestamp":1729526630000},"page":"420-437","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["PartCraft: Crafting Creative Objects by\u00a0Parts"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9309-563X","authenticated-orcid":false,"given":"Kam Woh","family":"Ng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9284-2955","authenticated-orcid":false,"given":"Xiatian","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5908-3275","authenticated-orcid":false,"given":"Yi-Zhe","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Xiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,22]]},"reference":[{"key":"23_CR1","doi-asserted-by":"crossref","unstructured":"Alaluf, Y., Richardson, E., Metzer, G., Cohen-Or, D.: A neural space-time representation for text-to-image personalization. arXiv preprint arXiv:2305.15391 (2023)","DOI":"10.1145\/3618322"},{"key":"23_CR2","doi-asserted-by":"crossref","unstructured":"Amir, S., Gandelsman, Y., Bagon, S., Dekel, T.: On the effectiveness of ViT features as local semantic descriptors. In: ECCV (2022)","DOI":"10.1007\/978-3-031-25069-9_3"},{"key":"23_CR3","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)","DOI":"10.1145\/3610548.3618154"},{"key":"23_CR4","doi-asserted-by":"crossref","unstructured":"Avrahami, O., Fried, O., Lischinski, D.: Blended latent diffusion. ACM TOG (2023)","DOI":"10.1145\/3592450"},{"key":"23_CR5","doi-asserted-by":"crossref","unstructured":"Avrahami, O., et al.: SpaText: Spatio-textual representation for controllable image generation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01762"},{"key":"23_CR6","unstructured":"Balaji, et\u00a0al.: eDiff-I: text-to-image diffusion models with an ensemble of expert denoisers. arXiv preprint arXiv:2211.01324 (2022)"},{"key":"23_CR7","unstructured":"Bar-Tal, O., Yariv, L., Lipman, Y., Dekel, T.: MultiDiffusion: fusing diffusion paths for controlled image generation. In: ICML (2023)"},{"key":"23_CR8","doi-asserted-by":"crossref","unstructured":"Biederman, I.: Recognition-by-components: a theory of human image understanding. Psychological review (1987)","DOI":"10.1037\/\/0033-295X.94.2.115"},{"key":"23_CR9","doi-asserted-by":"publisher","first-page":"422","DOI":"10.1016\/j.ijhcs.2005.04.006","volume":"63","author":"N Bonnardel","year":"2005","unstructured":"Bonnardel, N., Marm\u00e8che, E.: Towards supporting evocation processes in creative design: a cognitive approach. Int. J. Hum. Comput. Stud. 63, 422\u2013435 (2005)","journal-title":"Int. J. Hum. Comput. Stud."},{"key":"23_CR10","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":"23_CR11","doi-asserted-by":"crossref","unstructured":"Caron, M., Touvron, H., Misra, I., J\u00e9gou, H., Mairal, J., Bojanowski, P., Joulin, A.: Emerging properties in self-supervised vision transformers. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"23_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3475799","volume":"18","author":"E Cetinic","year":"2022","unstructured":"Cetinic, E., She, J.: Understanding and creating art with AI: review and outlook. ACM Trans. Multimedia Comput. Commun. Appl. 18, 1\u201322 (2022)","journal-title":"ACM Trans. Multimedia Comput. Commun. Appl."},{"key":"23_CR13","doi-asserted-by":"crossref","unstructured":"Chefer, H., Alaluf, Y., Vinker, Y., Wolf, L., Cohen-Or, D.: Attend-and-excite: attention-based semantic guidance for text-to-image diffusion models. ACM TOG (2023)","DOI":"10.1145\/3592116"},{"key":"23_CR14","unstructured":"Chen, C., Li, O., Tao, D., Barnett, A., Rudin, C., Su, J.K.: This looks like that: deep learning for interpretable image recognition. In: NeurIPS (2019)"},{"key":"23_CR15","doi-asserted-by":"crossref","unstructured":"Chen, M., Laina, I., Vedaldi, A.: Training-free layout control with cross-attention guidance (2024)","DOI":"10.1109\/WACV57701.2024.00526"},{"key":"23_CR16","doi-asserted-by":"crossref","unstructured":"Cintas, C., Das, P., Quanz, B., Tadesse, G.A., Speakman, S., Chen, P.Y.: Towards creativity characterization of generative models via group-based subset scanning. In: IJCAI (2022)","DOI":"10.24963\/ijcai.2022\/683"},{"key":"23_CR17","unstructured":"Couairon, G., Verbeek, J., Schwenk, H., Cord, M.: DiffEdit: diffusion-based semantic image editing with mask guidance. In: ICLR (2023)"},{"key":"23_CR18","doi-asserted-by":"crossref","unstructured":"Das, P., Quanz, B., Chen, P.Y., Ahn, J., Shah, D.: Toward a neuro-inspired creative decoder. In: IJCAI (2020)","DOI":"10.24963\/ijcai.2020\/381"},{"key":"23_CR19","unstructured":"Ding, M., et\u00a0al.: CogView: mastering text-to-image generation via transformers. In: NeurIPS (2021)"},{"key":"23_CR20","unstructured":"Ding, M., Zheng, W., Hong, W., Tang, J.: CogView2: faster and better text-to-image generation via hierarchical transformers. In: NeurIPS, vol.\u00a035 (2022)"},{"key":"23_CR21","unstructured":"Elgammal, A., Liu, B., Elhoseiny, M., Mazzone, M.: CAN: creative adversarial networks generating \u201cart\u201d by learning about styles and deviating from style norms. In: ICCC (2017)"},{"key":"23_CR22","doi-asserted-by":"crossref","unstructured":"Felzenszwalb, P.F., Huttenlocher, D.P.: Pictorial structures for object recognition. IJCV (2005)","DOI":"10.1023\/B:VISI.0000042934.15159.49"},{"key":"23_CR23","unstructured":"Feng, W., et al.: Training-free structured diffusion guidance for compositional text-to-image synthesis. In: ICLR (2022)"},{"key":"23_CR24","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 (2022)","DOI":"10.1007\/978-3-031-19784-0_6"},{"key":"23_CR25","unstructured":"Gal, R., et al.: An image is worth one word: Personalizing text-to-image generation using textual inversion. In: ICLR (2023)"},{"key":"23_CR26","unstructured":"Ge, S., Goswami, V., Zitnick, C.L., Parikh, D.: Creative sketch generation. In: ICLR (2021)"},{"key":"23_CR27","doi-asserted-by":"crossref","unstructured":"He, J., Chen, J., Lin, M.X., Yu, Q., Yuille, A.L.: Compositor: bottom-up clustering and compositing for robust part and object segmentation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01083"},{"key":"23_CR28","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":"23_CR29","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local NASH equilibrium. In: NeurIPS, vol. 30 (2017)"},{"key":"23_CR30","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: NeurIPS (2020)"},{"key":"23_CR31","unstructured":"Hu, E.J., et al.: LoRA: low-rank adaptation of large language models. In: ICLR (2022)"},{"key":"23_CR32","doi-asserted-by":"crossref","unstructured":"Kawar, B., Zada, S., Lang, O., Tov, O., Chang, H., Dekel, T., Mosseri, I., Irani, M.: Imagic: text-based real image editing with diffusion models. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"23_CR33","unstructured":"Khosla, A., Jayadevaprakash, N., Yao, B., Li, F.F.: Novel dataset for fine-grained image categorization: Stanford dogs. In: CVPRW (2011)"},{"key":"23_CR34","doi-asserted-by":"crossref","unstructured":"Kim, Y., Lee, J., Kim, J.H., Ha, J.W., Zhu, J.Y.: Dense text-to-image generation with attention modulation. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00708"},{"key":"23_CR35","doi-asserted-by":"crossref","unstructured":"Krause, J., Jin, H., Yang, J., Fei-Fei, L.: Fine-grained recognition without part annotations. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7299194"},{"key":"23_CR36","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":"23_CR37","unstructured":"Li, B., Qi, X., Lukasiewicz, T., Torr, P.: Controllable text-to-image generation. In: NeurIPS (2019)"},{"key":"23_CR38","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: GLIGEN: open-set grounded text-to-image generation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"23_CR39","unstructured":"Van\u00a0der Maaten, L., Hinton, G.: Visualizing data using T-SNE. J. Mach. Learn. Res. 9, 2579\u20132605 (2008)"},{"key":"23_CR40","doi-asserted-by":"crossref","unstructured":"Mo, S., Mu, F., Lin, K.H., Liu, Y., Guan, B., Li, Y., Zhou, B.: FreeControl: training-free spatial control of any text-to-image diffusion model with any condition. arXiv preprint arXiv:2312.07536 (2023)","DOI":"10.1109\/CVPR52733.2024.00713"},{"key":"23_CR41","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":"23_CR42","doi-asserted-by":"crossref","unstructured":"Nagai, Y., Taura, T., Mukai, F.: Concept blending and dissimilarity: factors for creative concept generation process. Design studies (2009)","DOI":"10.1016\/j.destud.2009.05.004"},{"key":"23_CR43","unstructured":"Nichol, A., et al.: Glide: towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741 (2021)"},{"key":"23_CR44","unstructured":"Nobari, A.H., Rashad, M.F., Ahmed, F.: CreativeGAN: editing generative adversarial networks for creative design synthesis. arXiv preprint arXiv:2103.06242 (2021)"},{"key":"23_CR45","unstructured":"Oquab, M., et al.: DINOv2: learning robust visual features without supervision (2023)"},{"key":"23_CR46","doi-asserted-by":"crossref","unstructured":"Qiao, T., Zhang, J., Xu, D., Tao, D.: MirrorGAN: learning text-to-image generation by redescription. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00160"},{"key":"23_CR47","unstructured":"Qu, Z., Xiang, T., Song, Y.Z.: SketchDreamer: interactive text-augmented creative sketch ideation. In: BMVC (2023)"},{"key":"23_CR48","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"23_CR49","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":"23_CR50","unstructured":"Ren, T., et al.: Grounded SAM: assembling open-world models for diverse visual tasks. arXiv preprint arXiv:2401.14159 (2024)"},{"key":"23_CR51","doi-asserted-by":"crossref","unstructured":"Richardson, E., Goldberg, K., Alaluf, Y., Cohen-Or, D.: ConceptLab: creative generation using diffusion prior constraints. arXiv preprint arXiv:2308.02669 (2023)","DOI":"10.1145\/3659578"},{"key":"23_CR52","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"23_CR53","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":"23_CR54","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1080\/10400419.2012.650092","volume":"24","author":"MA Runco","year":"2012","unstructured":"Runco, M.A., Jaeger, G.J.: The standard definition of creativity. Creativity Res. J. 24, 92\u201396 (2012)","journal-title":"Creativity Res. J."},{"key":"23_CR55","unstructured":"Saharia, C., et\u00a0al.: Photorealistic text-to-image diffusion models with deep language understanding. In: NeurIPS, vol.\u00a035 (2022)"},{"key":"23_CR56","doi-asserted-by":"crossref","unstructured":"Sbai, O., Elhoseiny, M., Bordes, A., LeCun, Y., Couprie, C.: Design: design inspiration from generative networks. In: ECCVW (2019)","DOI":"10.1007\/978-3-030-11015-4_5"},{"key":"23_CR57","unstructured":"Sun, P., Chen, S., Luo, P.: Grounded segment anything: from objects to parts. https:\/\/github.com\/Cheems-Seminar\/grounded-segment-any-parts (2023)"},{"key":"23_CR58","doi-asserted-by":"crossref","unstructured":"Sun, P., et al.: Going denser with open-vocabulary part segmentation. arXiv preprint arXiv:2305.11173 (2023)","DOI":"10.1109\/ICCV51070.2023.01417"},{"key":"23_CR59","doi-asserted-by":"crossref","unstructured":"Tao, M., Tang, H., Wu, F., Jing, X.Y., Bao, B.K., Xu, C.: DF-GAN: a simple and effective baseline for text-to-image synthesis. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01602"},{"key":"23_CR60","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)","DOI":"10.1145\/3618315"},{"key":"23_CR61","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":"23_CR62","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The Caltech-UCSD Birds-200-2011 Dataset (2011)"},{"key":"23_CR63","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":"23_CR64","doi-asserted-by":"crossref","unstructured":"Wei, Y., Zhang, Y., Ji, Z., Bai, J., Zhang, L., Zuo, W.: Elite: Encoding visual concepts into textual embeddings for customized text-to-image generation. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01461"},{"key":"23_CR65","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1006\/jmla.2000.2772","volume":"45","author":"MJ Wilkenfeld","year":"2001","unstructured":"Wilkenfeld, M.J., Ward, T.B.: Similarity and emergence in conceptual combination. J. Memory Lang. 45, 21\u201338 (2001)","journal-title":"J. Memory Lang."},{"key":"23_CR66","doi-asserted-by":"crossref","unstructured":"Xie, J., et al.: BoxDiff: text-to-image synthesis with training-free box-constrained diffusion. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00685"},{"key":"23_CR67","doi-asserted-by":"crossref","unstructured":"Xu, T., et al.: AttnGAN: fine-grained text to image generation with attentional generative adversarial networks. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00143"},{"key":"23_CR68","doi-asserted-by":"crossref","unstructured":"Yang, B., et al.: Paint by example: exemplar-based image editing with diffusion models. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01763"},{"key":"23_CR69","doi-asserted-by":"crossref","unstructured":"Yang, Z., et\u00a0al.: ReCo: region-controlled text-to-image generation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01369"},{"key":"23_CR70","doi-asserted-by":"crossref","unstructured":"Yin, G., Liu, B., Sheng, L., Yu, N., Wang, X., Shao, J.: Semantics disentangling for text-to-image generation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00243"},{"key":"23_CR71","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"23_CR72","doi-asserted-by":"crossref","unstructured":"Zhu, M., Pan, P., Chen, W., Yang, Y.: DM-GAN: dynamic memory generative adversarial networks for text-to-image synthesis. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00595"}],"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\/978-3-031-72673-6_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T16:10:38Z","timestamp":1729527038000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72673-6_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,22]]},"ISBN":["9783031726729","9783031726736"],"references-count":72,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72673-6_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,22]]},"assertion":[{"value":"22 October 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"}}]}}