ArXiv.org最新文献

筛选

英文中文

X-Humanoid: Robotize Human Videos to Generate Humanoid Videos at Scale X-Humanoid：机器人化人类视频以大规模生成人形视频

ArXiv.org Pub Date : 2025-12-04 DOI: 10.48550/arxiv.2512.04537

Pei Yang, Hai Ci, Yiren Song, Mike Zheng Shou

{"title":"X-Humanoid: Robotize Human Videos to Generate Humanoid Videos at Scale","authors":"Pei Yang, Hai Ci, Yiren Song, Mike Zheng Shou","doi":"10.48550/arxiv.2512.04537","DOIUrl":"https://doi.org/10.48550/arxiv.2512.04537","url":null,"abstract":"The advancement of embodied AI has unlocked significant potential for intelligent humanoid robots. However, progress in both Vision-Language-Action (VLA) models and world models is severely hampered by the scarcity of large-scale, diverse training data. A promising solution is to \"robotize\" web-scale human videos, which has been proven effective for policy training. However, these solutions mainly \"overlay\" robot arms to egocentric videos, which cannot handle complex full-body motions and scene occlusions in third-person videos, making them unsuitable for robotizing humans. To bridge this gap, we introduce X-Humanoid, a generative video editing approach that adapts the powerful Wan 2.2 model into a video-to-video structure and finetunes it for the human-to-humanoid translation task. This finetuning requires paired human-humanoid videos, so we designed a scalable data creation pipeline, turning community assets into 17+ hours of paired synthetic videos using Unreal Engine. We then apply our trained model to 60 hours of the Ego-Exo4D videos, generating and releasing a new large-scale dataset of over 3.6 million \"robotized\" humanoid video frames. Quantitative analysis and user studies confirm our method's superiority over existing baselines: 69% of users rated it best for motion consistency, and 62.1% for embodiment correctness.","PeriodicalId":523076,"journal":{"name":"ArXiv.org","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://arxiv.org/pdf/2512.04537","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147909291","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0