{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:19:29Z","timestamp":1778080769858,"version":"3.51.4"},"reference-count":73,"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\/iccvw69036.2025.00201","type":"proceedings-article","created":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T20:44:02Z","timestamp":1771879442000},"page":"1916-1926","source":"Crossref","is-referenced-by-count":3,"title":["DreamHOI: Subject-Driven Generation of 3D Human-Object Interactions with Diffusion Priors"],"prefix":"10.1109","author":[{"given":"Hanwen","family":"Zhu","sequence":"first","affiliation":[{"name":"University of Oxford"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruining","family":"Li","sequence":"additional","affiliation":[{"name":"University of Oxford"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomas","family":"Jakab","sequence":"additional","affiliation":[{"name":"University of Oxford"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01547"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"ref3","article-title":"SMPLitex: A Gen-erative Model and Dataset for 3D Human Texture Estimation from Single Image","author":"Casas","year":"2023","journal-title":"BMVC"},{"key":"ref4","article-title":"Layered construction for deformable animated charac-ters","author":"John","year":"1989","journal-title":"ACM SIGGRAPH"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72691-0_8"},{"key":"ref6","article-title":"In-terfusion: Text-driven generation of 3d human-object inter-action","author":"Dai","year":"2024","journal-title":"ECCV"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01880"},{"key":"ref8","article-title":"Compositional visual generation with energy based models","author":"Du","year":"2020","journal-title":"NeurIPS"},{"key":"ref9","volume-title":"Scaling rectified flow trans-formers for high-resolution image synthesis","author":"Esser","year":"2024"},{"key":"ref10","article-title":"Cat3d: Create anything in 3d with multi-view diffusion models","author":"Gao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01447"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref13","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00881"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00051"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00859"},{"key":"ref18","volume-title":"DeepFloyd Lab. If","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3618333"},{"key":"ref20","article-title":"Instant3D: Fast text-to-3D with sparse-view generation and large reconstruction model","author":"Li","year":"2024","journal-title":"ICLR"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72627-9_10"},{"key":"ref22","article-title":"Puppet-master: Scaling interactive video gen-eration as a motion prior for part-level dynamics","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00931"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_26"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/BF01914864"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00816"},{"key":"ref30","article-title":"Im-3d: Iterative multiview diffusion and reconstruction for high-quality 3d generation","author":"Melas-Kyriazi","year":"2024","journal-title":"ICLR"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref32","article-title":"Gpt-4 technical report","year":"2023","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_36"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw67362.2025.00271"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00026"},{"key":"ref37","article-title":"DreamFusion: Text-to-3d using 2d diffusion","author":"Poole","year":"2023","journal-title":"ICLR"},{"key":"ref38","article-title":"Learning transferable visual models from natural language super-vision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130883"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00856"},{"key":"ref42","article-title":"MVDream: Multi-view diffusion for 3D generation","author":"Shi","year":"2024","journal-title":"ICLR"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.494"},{"key":"ref44","article-title":"Deep-voxels: Learning persistent 3d feature embeddings","author":"Sitzmann","year":"2019","journal-title":"CVPR"},{"key":"ref45","volume-title":"Sketchfab. Sketchfab","year":"2024"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/1276377.1276478"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00972"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_34"},{"key":"ref49","article-title":"Dreamgaussian: Generative gaussian splatting for ef-ficient 3d content creation","author":"Tang","year":"2024","journal-title":"ICLR"},{"key":"ref50","article-title":"Human motion diffusion model","author":"Tevet","year":"2022","journal-title":"ICLR"},{"key":"ref51","article-title":"Cg3d: Compositional generation for text-to-3d via gaussian splatting","author":"Vilesov","year":"2023","journal-title":"arXiv preprint"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_25"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01214"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_4"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73247-8_27"},{"key":"ref56","article-title":"Prolificdreamer: High-fidelity and diverse text-to-3d generation with variational score distillation","author":"Wang","year":"2023","journal-title":"NeurIPS"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.511"},{"key":"ref58","article-title":"Thor: Text to human-object inter-action diffusion via relation intervention","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00008"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01819-5"},{"key":"ref61","article-title":"Magicpony: Learning articu-lated 3d animals in the wild","author":"Wu","year":"2023","journal-title":"CVPR"},{"key":"ref62","article-title":"D3d-hoi: Dynamic 3d human-object interactions from videos","author":"Xu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02033"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00455"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00652"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20065-6_30"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00623"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_18"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00928"},{"key":"ref70","article-title":"Pamir: Parametric model-conditioned implicit representation for image-based human reconstruction","author":"Zheng","year":"2021","journal-title":"PAMI"},{"key":"ref71","article-title":"Gala3d: Towards text-to-3d complex scene generation via layout-guided generative gaussian splatting","author":"Zhou","year":"2024","journal-title":"ICML"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.586"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00514"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,20]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11373940\/11374285\/11375329.pdf?arnumber=11375329","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T07:34:16Z","timestamp":1771918456000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11375329\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":73,"URL":"https:\/\/doi.org\/10.1109\/iccvw69036.2025.00201","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}