{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:12:11Z","timestamp":1784268731225,"version":"3.55.0"},"reference-count":86,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002551","name":"Seoul National University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002551","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01119","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"12034-12044","source":"Crossref","is-referenced-by-count":1,"title":["PersonaCraft: Personalized and Controllable Full-Body Multi-Human Scene Generation Using Occlusion-Aware 3D-Conditioned Diffusion"],"prefix":"10.1109","author":[{"given":"Gwanghyun","family":"Kim","sequence":"first","affiliation":[{"name":"Dept. of Electrical and Computer Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Suh Yoon","family":"Jeon","sequence":"additional","affiliation":[{"name":"Dept. of Electrical and Computer Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seunggyu","family":"Lee","sequence":"additional","affiliation":[{"name":"Dept. of Electrical and Computer Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Se Young","family":"Chun","sequence":"additional","affiliation":[{"name":"Dept. of Electrical and Computer Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Insightface: 2d and 3d face analysis project","volume-title":"Github"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3618322"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.471"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618173"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618154"},{"key":"ref6","article-title":"Multidiffusion: Fusing diffusion paths for controlled image generation","author":"Bar-Tal","year":"2023","journal-title":"arXiv preprint"},{"key":"ref7","article-title":"Multi-hmr: Multi-person whole-body human mesh recovery in a single shot","year":"2024","journal-title":"ECCV"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73337-6_12"},{"issue":"3","key":"ref9","article-title":"Improving image generation with better captions","volume":"2","author":"Betker","year":"2023","journal-title":"Computer Science"},{"key":"ref10","author":"Bi\u0144kowski","journal-title":"Demystifying mmd gans"},{"key":"ref11","article-title":"Controlling human shape and pose in text-to-image diffusion models via domain adaptation","author":"Buchheim","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"ref13","article-title":"Instructbooth: Instruction-following personalized text-to-image generation","author":"Chae","year":"2023","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"Subject-driven text-to-image generation via apprenticeship learning","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00630"},{"key":"ref16","article-title":"Custom-edit: Text-guided image editing with customized diffusion models","author":"Choi","year":"2023","journal-title":"arXiv preprint"},{"key":"ref17","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","author":"Gal","year":"2022","journal-title":"ICLR"},{"key":"ref18","article-title":"Designing an encoder for fast personalization of text-to-image models","author":"Gal","year":"2023","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3592133"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618184"},{"key":"ref21","article-title":"Mix-of-show: Decentralized lowrank adaptation for multi-concept customization of diffusion models","author":"Gu","year":"2023","journal-title":"NeurIPS"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00762"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00673"},{"key":"ref24","article-title":"Vico: Detail-preserving visual condition for personalized text-to-image generation","author":"Hao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref25","article-title":"Uniportrait: A unified framework for identity-preserving singleand multi-human image personalization","author":"He","year":"2024","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00372"},{"key":"ref27","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref28","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"ICLR"},{"issue":"7","key":"ref29","first-page":"1325","article-title":"Human3","volume":"36","author":"Ionescu","year":"2013","journal-title":"6 m: Large scale datasets and predictive methods for 3d human sensing in natural environments. TPAMI"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_12"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01465"},{"key":"ref32","author":"Khan","year":"2024","journal-title":"Focusclip: Multimodal subject-level guidance for zero-shot transfer in human-centric tasks"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01365"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00246"},{"key":"ref35","first-page":"22603","article-title":"Podia3d: Domain adaptation of 3d generative model across large domain gap using pose-preserved text-to-image diffusion","author":"Kim","year":"2023","journal-title":"CVPR"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73039-9_8"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72751-1_15"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.663"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref40","first-page":"122458","article-title":"Applying guidance in a limited interval improves sample and distribution quality in diffusion models","volume":"37","author":"Kynk\u00e4\u00e4nniemi","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref41","volume-title":"Flux","year":"2024"},{"key":"ref42","article-title":"Blip2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00825"},{"key":"ref44","article-title":"Hyperhuman: Hyper-realistic human generation with latent structural diffusion","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref45","article-title":"Cones 2: Customizable image synthesis with multiple subjects","volume-title":"arXiv preprint","author":"Liu","year":"2023"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"key":"ref47","article-title":"Unified multi-modal latent diffusion for joint subject and text conditional image generation","author":"Ma","year":"2023","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01973"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref50","article-title":"Cross initialization for personalized text-to-image generation","author":"Pang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"ref52","journal-title":"Smpl made simple faqs"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00761"},{"key":"ref54","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","volume-title":"arXiv preprint","author":"Podell","year":"2023"},{"key":"ref55","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00624"},{"key":"ref58","article-title":"Eliminating oversaturation and artifacts of high guidance scales in diffusion models","author":"Sadat","year":"2024","journal-title":"ICLR"},{"key":"ref59","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","author":"Saharia","year":"2022","journal-title":"NeurIPS"},{"key":"ref60","article-title":"Improved techniques for training gans","author":"Salimans","year":"2016","journal-title":"NeurIPS, 29"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00895"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00816"},{"key":"ref64","article-title":"Continual diffusion: Continual customization of text-to-image diffusion with c-lora","author":"Seale Smith","year":"2023","journal-title":"arXiv preprint"},{"key":"ref65","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"ICLR"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591506"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3618315"},{"key":"ref68","article-title":"p+: Extended textual conditioning in text-to-image generation","author":"Voynov","year":"2023","journal-title":"arXiv preprint"},{"key":"ref69","first-page":"65670","article-title":"Stable-pose: Leveraging transformers for pose-guided text-to-image generation","volume":"37","author":"Wang","year":"2025","journal-title":"NeurIPS"},{"key":"ref70","article-title":"Instantid: Zero-shot identity-preserving generation in seconds","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref71","author":"Wang","year":"2024","journal-title":"Instantid: Zero-shot identity-preserving generation in seconds"},{"key":"ref72","article-title":"Ms-diffusion: Multi-subject zero-shot image personalization with layout guidance","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01461"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02227-z"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02227-z"},{"key":"ref76","article-title":"Facestudio: Put your face everywhere in seconds","author":"Yan","year":"2023","journal-title":"arXiv preprint"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00455"},{"key":"ref78","article-title":"Ipadapter: Text compatible image prompt adapter for text-toimage diffusion models","author":"Ye","journal-title":"2023"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28565"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00284"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2025.3531917"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00877"},{"key":"ref84","article-title":"Enhancing detail preservation for customized text-to-image generation: A regularization-free approach","author":"Zhou","year":"2023","journal-title":"arXiv preprint"},{"key":"ref85","article-title":"Storymaker: Towards holistic consistent characters in text-to-image generation","author":"Zhou","year":"2024","journal-title":"arXiv preprint"},{"key":"ref86","article-title":"Champ: Controllable and consistent human image animation with 3d parametric guidance","author":"Zhu","year":"2024","journal-title":"arXiv preprint"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444512.pdf?arnumber=11444512","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:53:31Z","timestamp":1777611211000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444512\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":86,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01119","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}