{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T16:50:16Z","timestamp":1777567816008,"version":"3.51.4"},"publisher-location":"Singapore","reference-count":36,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819786190","type":"print"},{"value":"9789819786206","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T00:00:00Z","timestamp":1729382400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T00:00:00Z","timestamp":1729382400000},"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\/978-981-97-8620-6_10","type":"book-chapter","created":{"date-parts":[[2024,10,19]],"date-time":"2024-10-19T21:02:10Z","timestamp":1729371730000},"page":"143-157","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Mixture-of-Hand-Experts: Repainting the Deformed Hand Images Generated by Diffusion Models"],"prefix":"10.1007","author":[{"given":"Yuxuan","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianwei","family":"Cao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kongming","family":"Liang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongjiang","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongxiang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhanyu","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,20]]},"reference":[{"key":"10_CR1","unstructured":"Bhat, S.F., Birkl, R., Wofk, D., Wonka, P., M\u00fcller, M.: Zoedepth: Zero-shot transfer by combining relative and metric depth (2023). arXiv:2302.12288"},{"key":"10_CR2","unstructured":"Cao, P., Zhou, F., Song, Q., Yang, L.: Controllable generation with text-to-image diffusion models: a survey (2024). arXiv:2403.04279"},{"key":"10_CR3","doi-asserted-by":"crossref","unstructured":"Cao, Z., Simon, T., Wei, S.E., Sheikh, Y.: Realtime multi-person 2d pose estimation using part affinity fields. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7291\u20137299 (2017)","DOI":"10.1109\/CVPR.2017.143"},{"key":"10_CR4","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et\u00a0al.: An image is worth 16x16 words: Transformers for image recognition at scale (2020). arXiv:2010.11929"},{"key":"10_CR5","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. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"10_CR6","unstructured":"Huang, L., Chen, D., Liu, Y., Shen, Y., Zhao, D., Zhou, J.: Composer: Creative and controllable image synthesis with composable conditions (2023). arXiv:2302.09778"},{"issue":"1","key":"10_CR7","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1162\/neco.1991.3.1.79","volume":"3","author":"RA Jacobs","year":"1991","unstructured":"Jacobs, R.A., Jordan, M.I., Nowlan, S.J., Hinton, G.E.: Adaptive mixtures of local experts. Neural Comput. 3(1), 79\u201387 (1991)","journal-title":"Neural Comput."},{"key":"10_CR8","doi-asserted-by":"crossref","unstructured":"Ju, X., Zeng, A., Zhao, C., Wang, J., Zhang, L., Xu, Q.: Humansd: A native skeleton-guided diffusion model for human image generation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15988\u201315998 (2023)","DOI":"10.1109\/ICCV51070.2023.01465"},{"key":"10_CR9","unstructured":"Kapitanov, A., Kvanchiani, K., Nagaev, A., Kraynov, R., Makhliarchuk, A.: Hagrid\u2013hand gesture recognition image dataset. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 4572\u20134581 (2024)"},{"key":"10_CR10","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning. PMLR, pp. 12888\u201312900 (2022)"},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"Lin, K., Wang, L., Liu, Z.: Mesh graphormer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12939\u201312948 (2021)","DOI":"10.1109\/ICCV48922.2021.01270"},{"key":"10_CR12","doi-asserted-by":"crossref","unstructured":"Lu, W., Xu, Y., Zhang, J., Wang, C., Tao, D.: Handrefiner: Refining malformed hands in generated images by diffusion-based conditional inpainting (2023). arXiv:2311.17957","DOI":"10.1145\/3664647.3680693"},{"key":"10_CR13","doi-asserted-by":"crossref","unstructured":"Mou, C., Wang, X., Xie, L., Wu, Y., Zhang, J., Qi, Z., Shan, Y.: T2i-adapter: learning adapters to dig out more controllable ability for text-to-image diffusion models. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 4296\u20134304 (2024)","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"10_CR14","unstructured":"Narasimhaswamy, S., Bhattacharya, U., Chen, X., Dasgupta, I., Mitra, S.: Text-to-hand-image generation using pose-and mesh-guided diffusion. In: IEEE\/CVF International Conference on Computer Vision (ICCV) 7th International Workshop on Observing and Understanding Hands in Action (2023)"},{"key":"10_CR15","doi-asserted-by":"crossref","unstructured":"Narasimhaswamy, S., Bhattacharya, U., Chen, X., Dasgupta, I., Mitra, S., Hoai, M.: Handiffuser: text-to-image generation with realistic hand appearances (2024). arXiv:2403.01693","DOI":"10.1109\/CVPR52733.2024.00239"},{"key":"10_CR16","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., Shan, D., Radosavovic, I., Kanazawa, A., Fouhey, D., Malik, J.: Reconstructing hands in 3d with transformers (2023). arXiv:2312.05251","DOI":"10.1109\/CVPR52733.2024.00938"},{"key":"10_CR17","doi-asserted-by":"crossref","unstructured":"Pelykh, A., Sincan, O.M., Bowden, R.: Giving a hand to diffusion models: a two-stage approach to improving conditional human image generation (2024). arXiv:2403.10731","DOI":"10.1109\/FG59268.2024.10582008"},{"key":"10_CR18","unstructured":"Podell, D., English, Z., Lacey, K., Blattmann, A., Dockhorn, T., M\u00fcller, J., Penna, J., Rombach, R.: Sdxl: Improving latent diffusion models for high-resolution image synthesis (2023). arXiv:2307.01952"},{"key":"10_CR19","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents (2022). arXiv:2204.061251(2), 3 (2022)"},{"issue":"3","key":"10_CR20","doi-asserted-by":"publisher","first-page":"1623","DOI":"10.1109\/TPAMI.2020.3019967","volume":"44","author":"R Ranftl","year":"2020","unstructured":"Ranftl, R., Lasinger, K., Hafner, D., Schindler, K., Koltun, V.: Towards robust monocular depth estimation: mixing datasets for zero-shot cross-dataset transfer. IEEE Trans. Pattern Anal. Mach. Intell. 44(3), 1623\u20131637 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10_CR21","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":"10_CR22","unstructured":"Romero, J., Tzionas, D., Black, M.J.: Embodied hands: modeling and capturing hands and bodies together (2022). arXiv:2201.02610"},{"key":"10_CR23","first-page":"36479","volume":"35","author":"C Saharia","year":"2022","unstructured":"Saharia, C., Chan, W., Saxena, S., Li, L., Whang, J., Denton, E.L., Ghasemipour, K., Gontijo Lopes, R., Karagol Ayan, B., Salimans, T., et al.: Photorealistic text-to-image diffusion models with deep language understanding. Adv. Neural. Inf. Process. Syst. 35, 36479\u201336494 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"10_CR24","doi-asserted-by":"crossref","unstructured":"Shao, H., Xu, Q., Wen, P., Gao, P., Yang, Z., Huang, Q.: Building bridge across the time: Disruption and restoration of murals in the wild. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 20259\u201320269 (2023)","DOI":"10.1109\/ICCV51070.2023.01853"},{"key":"10_CR25","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models (2020). arXiv:2010.02502"},{"key":"10_CR26","unstructured":"Sutherland, J., Arbel, M., Gretton, A.: Demystifying mmd GANs. In: International Conference for Learning Representations, pp. 1\u201336 (2018)"},{"key":"10_CR27","unstructured":"Vakunov, A., Chang, C.L., Zhang, F., Sung, G., Grundmann, M., Bazarevsky, V.: Mediapipe hands: on-device real-time hand tracking. In: CVPR Workshop (2020)"},{"key":"10_CR28","doi-asserted-by":"crossref","unstructured":"Wu, C., Wang, D., Bai, Y., Mao, H., Li, Y., Shen, Q.: Hsr-diff: hyperspectral image super-resolution via conditional diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7083\u20137093 (2023)","DOI":"10.1109\/ICCV51070.2023.00652"},{"key":"10_CR29","unstructured":"Wu, X., Huang, S., Wei, F.: Mixture of lora experts (2024). arXiv:2404.13628"},{"key":"10_CR30","doi-asserted-by":"crossref","unstructured":"Xia, B., Zhang, Y., Wang, S., Wang, Y., Wu, X., Tian, Y., Yang, W., Van\u00a0Gool, L.: Diffir: efficient diffusion model for image restoration. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13095\u201313105 (2023)","DOI":"10.1109\/ICCV51070.2023.01204"},{"key":"10_CR31","unstructured":"Yang, Z., Xu, Q., Wang, Z., Li, S., Han, B., Bao, S., Cao, X., Huang, Q.: Harnessing hierarchical label distribution variations in test agnostic long-tail recognition (2024). arXiv:2405.07780"},{"key":"10_CR32","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":"10_CR33","unstructured":"Zhang, Y., Qin, Z., Liu, Y., Campbell, D.: Detecting and restoring non-standard hands in stable diffusion generated images (2023). arXiv:2312.04236"},{"key":"10_CR34","unstructured":"Zhao, S., Chen, D., Chen, Y.C., Bao, J., Hao, S., Yuan, L., Wong, K.Y.K.: Uni-controlnet: all-in-one control to text-to-image diffusion models. Advances in Neural Information Processing Systems 36 (2024)"},{"key":"10_CR35","doi-asserted-by":"crossref","unstructured":"Zimmermann, C., Brox, T.: Learning to estimate 3d hand pose from single RGB images. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4903\u20134911 (2017)","DOI":"10.1109\/ICCV.2017.525"},{"key":"10_CR36","doi-asserted-by":"crossref","unstructured":"Zimmermann, C., Ceylan, D., Yang, J., Russell, B., Argus, M., Brox, T.: Freihand: A dataset for markerless capture of hand pose and shape from single RGB images. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 813\u2013822 (2019)","DOI":"10.1109\/ICCV.2019.00090"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-8620-6_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,14]],"date-time":"2025-01-14T20:19:05Z","timestamp":1736885945000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8620-6_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,20]]},"ISBN":["9789819786190","9789819786206"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8620-6_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,20]]},"assertion":[{"value":"20 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Urumqi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"18 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2024.prcv.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}