Salvato in:
Dettagli Bibliografici
Autori principali: Xiu, Jingqiao, Hong, Fangzhou, Li, Yicong, Li, Mengze, Wang, Wentao, Han, Sirui, Pan, Liang, Liu, Ziwei
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2508.13013
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915449608863744
author Xiu, Jingqiao
Hong, Fangzhou
Li, Yicong
Li, Mengze
Wang, Wentao
Han, Sirui
Pan, Liang
Liu, Ziwei
author_facet Xiu, Jingqiao
Hong, Fangzhou
Li, Yicong
Li, Mengze
Wang, Wentao
Han, Sirui
Pan, Liang
Liu, Ziwei
contents While exocentric video synthesis has achieved great progress, egocentric video generation remains largely underexplored, which requires modeling first-person view content along with camera motion patterns induced by the wearer's body movements. To bridge this gap, we introduce a novel task of joint egocentric video and human motion generation, characterized by two key challenges: 1) Viewpoint Alignment: the camera trajectory in the generated video must accurately align with the head trajectory derived from human motion; 2) Causal Interplay: the synthesized human motion must causally align with the observed visual dynamics across adjacent video frames. To address these challenges, we propose EgoTwin, a joint video-motion generation framework built on the diffusion transformer architecture. Specifically, EgoTwin introduces a head-centric motion representation that anchors the human motion to the head joint and incorporates a cybernetics-inspired interaction mechanism that explicitly captures the causal interplay between video and motion within attention operations. For comprehensive evaluation, we curate a large-scale real-world dataset of synchronized text-video-motion triplets and design novel metrics to assess video-motion consistency. Extensive experiments demonstrate the effectiveness of the EgoTwin framework.
format Preprint
id arxiv_https___arxiv_org_abs_2508_13013
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle EgoTwin: Dreaming Body and View in First Person
Xiu, Jingqiao
Hong, Fangzhou
Li, Yicong
Li, Mengze
Wang, Wentao
Han, Sirui
Pan, Liang
Liu, Ziwei
Computer Vision and Pattern Recognition
While exocentric video synthesis has achieved great progress, egocentric video generation remains largely underexplored, which requires modeling first-person view content along with camera motion patterns induced by the wearer's body movements. To bridge this gap, we introduce a novel task of joint egocentric video and human motion generation, characterized by two key challenges: 1) Viewpoint Alignment: the camera trajectory in the generated video must accurately align with the head trajectory derived from human motion; 2) Causal Interplay: the synthesized human motion must causally align with the observed visual dynamics across adjacent video frames. To address these challenges, we propose EgoTwin, a joint video-motion generation framework built on the diffusion transformer architecture. Specifically, EgoTwin introduces a head-centric motion representation that anchors the human motion to the head joint and incorporates a cybernetics-inspired interaction mechanism that explicitly captures the causal interplay between video and motion within attention operations. For comprehensive evaluation, we curate a large-scale real-world dataset of synchronized text-video-motion triplets and design novel metrics to assess video-motion consistency. Extensive experiments demonstrate the effectiveness of the EgoTwin framework.
title EgoTwin: Dreaming Body and View in First Person
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.13013