{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:28:18Z","timestamp":1777865298783,"version":"3.51.4"},"reference-count":62,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01753","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"18866-18875","source":"Crossref","is-referenced-by-count":0,"title":["Teleportraits: Training-Free People Insertion Into Any Scene"],"prefix":"10.1109","author":[{"given":"Jialu","family":"Gao","sequence":"first","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"K J","family":"Joseph","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fernando","family":"De La Torre","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00590"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3592450"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_23"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00630"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73016-0_13"},{"key":"ref8","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72661-3_23"},{"key":"ref10","article-title":"Visual persona: Foundation model for fullbody human customization","author":"Nam","year":"2025","journal-title":"arXiv"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72684-2_11"},{"key":"ref12","article-title":"An image is worth one word: Personalizing text-toimage generation using textual inversion","author":"Gal","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72630-9_23"},{"key":"ref14","article-title":"The Ecological Approach to Visual Perception","author":"Gibson","year":"1979","journal-title":"Houghton Mifflin, Boston"},{"key":"ref15","volume-title":"Uniportrait: A unified framework for identity-preserving single- and multihuman image personalization","author":"He","year":"2024"},{"key":"ref16","volume-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022"},{"key":"ref17","volume-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020"},{"key":"ref18","volume-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72973-7_24"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01639"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1312"},{"key":"ref24","volume-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01265"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00825"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657469"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00585"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00774"},{"key":"ref30","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72913-3_14"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72646-0_4"},{"key":"ref33","volume-title":"Dreambench++: A human-aligned benchmark for personalized image generation","author":"Peng","year":"2025"},{"key":"ref34","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref35","volume-title":"Dreamfusion: Text-to-3d using 2d diffusion","author":"Poole","year":"2022"},{"key":"ref36","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i7.32729"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00621"},{"key":"ref42","volume-title":"Denoising diffusion implicit models","author":"Song","year":"2022"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0068"},{"key":"ref44","article-title":"Add-it: Training-free object insertion in images with pretrained diffusion models","author":"Tewel","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3658157"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10888013"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00928"},{"key":"ref48","volume-title":"Instantid: Zeroshot identity-preserving generation in seconds","author":"Wang","year":"2024"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2025.3613113"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.359"},{"key":"ref51","volume-title":"Magicface: Training-free universal-style human image customized synthesis","author":"Wang","year":"2024"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01461"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72983-6_15"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02227-z"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i9.32973"},{"key":"ref56","volume-title":"Facestudio: Put your face everywhere in seconds","author":"Yan","year":"2023"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612439"},{"key":"ref58","volume-title":"Ipadapter: Text compatible image prompt adapter for text-toimage diffusion models","author":"Ye","year":"2023"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3190"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33123"}],"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\/11444666.pdf?arnumber=11444666","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:12:29Z","timestamp":1777529549000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444666\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01753","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}