{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,24]],"date-time":"2025-08-24T00:02:17Z","timestamp":1755993737947,"version":"3.44.0"},"reference-count":74,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62132001"],"award-info":[{"award-number":["62132001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tip.2025.3597037","type":"journal-article","created":{"date-parts":[[2025,8,14]],"date-time":"2025-08-14T18:49:23Z","timestamp":1755197363000},"page":"5241-5256","source":"Crossref","is-referenced-by-count":0,"title":["Parts2Whole: Generalizable Multi-Part Portrait Customization"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-4525-8777","authenticated-orcid":false,"given":"Hongxing","family":"Fan","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Beihang University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1883-0777","authenticated-orcid":false,"given":"Zehuan","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Software, Beihang University, Beijing, China"}]},{"given":"Lipeng","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Software, Beihang University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4631-0172","authenticated-orcid":false,"given":"Haohua","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Software, Beihang University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2485-6506","authenticated-orcid":false,"given":"Li","family":"Yin","sequence":"additional","affiliation":[{"name":"School of Software, Beihang University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8525-9163","authenticated-orcid":false,"given":"Lu","family":"Sheng","sequence":"additional","affiliation":[{"name":"School of Software, Beihang University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2929257"},{"key":"ref2","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref3","first-page":"16784","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Nichol"},{"key":"ref4","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. NIPS","volume":"35","author":"Saharia"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref6","first-page":"22275","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Podell"},{"key":"ref7","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Dhariwal"},{"key":"ref8","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref9","first-page":"14205","article-title":"Denoising diffusion implicit models","volume-title":"Proc. 9th Int. Conf. Learn. Represent.","author":"Song"},{"key":"ref10","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv:2207.12598"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530104"},{"key":"ref12","first-page":"2251","article-title":"HyperHuman: Hyper-realistic human generation with latent structural diffusion","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Liu"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01391"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00243"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00578"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00451"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01465"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00664"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00614"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref21","first-page":"12513","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. 10th Int. Conf. Learn. Represent.","author":"Hu"},{"key":"ref22","first-page":"1069","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Gal"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref24","first-page":"21548","article-title":"Cones: Concept neurons in diffusion models for customized generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00816"},{"key":"ref26","article-title":"IP-adapter: Text compatible image prompt adapter for text-to-image diffusion models","author":"Ye","year":"2023","journal-title":"arXiv:2308.06721"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00630"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00825"},{"key":"ref29","article-title":"InstantID: Zero-shot identity-preserving generation in seconds","author":"Wang","year":"2024","journal-title":"arXiv:2401.07519"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00771"},{"key":"ref31","first-page":"15890","article-title":"Mix-of-show: Decentralized low rank adaptation for multi-concept customization of diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Gu"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00848"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00868"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00267"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33187"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72751-1_15"},{"key":"ref37","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref38","first-page":"51","article-title":"DwNet: Dense warp-based network for pose-guided human video generation","volume-title":"Proc. 30th Brit. Mach. Vis. Conf.","author":"Zablotskaia"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.124"},{"key":"ref40","first-page":"25278","article-title":"LAION-5B: An open large-scale dataset for training next generation image-text models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Schuhmann"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00134"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72673-6_23"},{"key":"ref43","article-title":"Chirpy3D: Creative fine-grained 3D object fabrication via part sampling","author":"Woh Ng","year":"2025","journal-title":"arXiv:2501.04144"},{"key":"ref44","article-title":"FastComposer: Tuning-free multi-subject image generation with localized attention","author":"Xiao","year":"2023","journal-title":"arXiv:2305.10431"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3687771"},{"article-title":"Auto-encoding variational Bayes","volume-title":"Proc. 2nd Int. Conf. Learn. Represent.","author":"Kingma","key":"ref46"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00779"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00147"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3658157"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00457"},{"key":"ref53","article-title":"Visual style prompting with swapping self-attention","author":"Jeong","year":"2024","journal-title":"arXiv:2402.12974"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01763"},{"volume-title":"Reference-Only Controlnet","year":"2023","author":"Zhang","key":"ref55"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618154"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00670"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"volume-title":"InsightFace: 2D and 3D Face Analysis Project","year":"2018","author":"Deng","key":"ref60"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00217"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00455"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00762"},{"volume-title":"Stable Diffusion Image Variations","year":"2022","key":"ref64"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref66","first-page":"1","article-title":"DINOv2: Learning robust visual features without supervision","volume":"2024","author":"Oquab","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref67","first-page":"50742","article-title":"DreamSim: Learning new dimensions of human visual similarity using synthetic data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Fu"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref70","first-page":"15903","article-title":"ImageReward: Learning and evaluating human preferences for text-to-image generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xu"},{"key":"ref71","first-page":"36652","article-title":"Pick-a-pic: An open dataset of user preferences for text-to-image generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kirstain"},{"key":"ref72","article-title":"Human preference score v2: A solid benchmark for evaluating human preferences of text-to-image synthesis","author":"Wu","year":"2023","journal-title":"arXiv:2306.09341"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00766"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00781"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10795784\/11125861.pdf?arnumber=11125861","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T01:06:30Z","timestamp":1755911190000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11125861\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":74,"URL":"https:\/\/doi.org\/10.1109\/tip.2025.3597037","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"type":"print","value":"1057-7149"},{"type":"electronic","value":"1941-0042"}],"subject":[],"published":{"date-parts":[[2025]]}}}