Pose-Faithful Facial Identity Preservation for Text-to-Video Generation</p>\n","updatedAt":"2026-05-13T08:19:30.235Z","author":{"_id":"6820a5143ccd1e0216105ff5","avatarUrl":"/avatars/4b65fadc31d72649b8c9c9958b992970.svg","fullname":"Yuanzhi Wang","name":"mdswyz","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.4064350426197052},"editors":["mdswyz"],"editorAvatarUrls":["/avatars/4b65fadc31d72649b8c9c9958b992970.svg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2605.04702","authors":[{"_id":"6a02e498b823258e761237f9","user":{"_id":"6820a5143ccd1e0216105ff5","avatarUrl":"/avatars/4b65fadc31d72649b8c9c9958b992970.svg","isPro":false,"fullname":"Yuanzhi Wang","user":"mdswyz","type":"user","name":"mdswyz"},"name":"Yuanzhi Wang","status":"claimed_verified","statusLastChangedAt":"2026-05-13T07:53:31.619Z","hidden":false},{"_id":"6a02e498b823258e761237fa","name":"Xuhua Ren","hidden":false},{"_id":"6a02e498b823258e761237fb","name":"Jiaxiang Cheng","hidden":false},{"_id":"6a02e498b823258e761237fc","name":"Bing Ma","hidden":false},{"_id":"6a02e498b823258e761237fd","name":"Kai Yu","hidden":false},{"_id":"6a02e498b823258e761237fe","name":"Sen Liang","hidden":false},{"_id":"6a02e498b823258e761237ff","name":"Wenyue Li","hidden":false},{"_id":"6a02e498b823258e76123800","name":"Tianxiang Zheng","hidden":false},{"_id":"6a02e498b823258e76123801","name":"Qinglin Lu","hidden":false},{"_id":"6a02e498b823258e76123802","name":"Zhen Cui","hidden":false}],"publishedAt":"2026-05-06T00:00:00.000Z","submittedOnDailyAt":"2026-05-13T00:00:00.000Z","title":"FaithfulFaces: Pose-Faithful Facial Identity Preservation for Text-to-Video Generation","submittedOnDailyBy":{"_id":"6820a5143ccd1e0216105ff5","avatarUrl":"/avatars/4b65fadc31d72649b8c9c9958b992970.svg","isPro":false,"fullname":"Yuanzhi Wang","user":"mdswyz","type":"user","name":"mdswyz"},"summary":"Identity-preserving text-to-video generation (IPT2V) empowers users to produce diverse and imaginative videos with consistent human facial identity. Despite recent progress, existing methods often suffer from significant identity distortion under large facial pose variations or facial occlusions. In this paper, we propose FaithfulFaces, a pose-faithful facial identity preservation learning framework to improve IPT2V in complex dynamic scenes. The key of FaithfulFaces is a pose-shared identity aligner that refines and aligns facial poses across distinct views via a pose-shared dictionary and a pose variation-identity invariance constraint. By mapping single-view inputs into a global facial pose representation with explicit Euler angle embeddings, FaithfulFaces provides a pose-faithful facial prior that guides generative foundations toward robust identity-preserving generation. In particular, we develop a specialized pipeline to curate a high-quality video dataset featuring substantial facial pose diversity. Extensive experiments demonstrate that FaithfulFaces achieves state-of-the-art performance, maintaining superior identity consistency and structural clarity even as pose changes and occlusions occur.","upvotes":1,"discussionId":"6a02e498b823258e76123803","ai_summary":" FaithfulFaces is a pose-faithful facial identity preservation framework that improves identity consistency in text-to-video generation through pose-shared alignment and explicit Euler angle embeddings.","ai_keywords":["pose-faithful facial identity preservation","pose-shared identity aligner","pose-shared dictionary","pose variation-identity invariance constraint","global facial pose representation","Euler angle embeddings","text-to-video generation","identity consistency","structural clarity"],"organization":{"_id":"6645f953c39288df638dbdd5","name":"Tencent-Hunyuan","fullname":"Tencent Hunyuan","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/62d22496c58f969c152bcefd/woKSjt2wXvBNKussyYPsa.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"620783f24e28382272337ba4","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/620783f24e28382272337ba4/zkUveQPNiDfYjgGhuFErj.jpeg","isPro":false,"fullname":"GuoLiangTang","user":"Tommy930","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"organization":{"_id":"6645f953c39288df638dbdd5","name":"Tencent-Hunyuan","fullname":"Tencent Hunyuan","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/62d22496c58f969c152bcefd/woKSjt2wXvBNKussyYPsa.png"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2605/2605.04702.md"}">
FaithfulFaces: Pose-Faithful Facial Identity Preservation for Text-to-Video Generation
Abstract
FaithfulFaces is a pose-faithful facial identity preservation framework that improves identity consistency in text-to-video generation through pose-shared alignment and explicit Euler angle embeddings.
AI-generated summary
Identity-preserving text-to-video generation (IPT2V) empowers users to produce diverse and imaginative videos with consistent human facial identity. Despite recent progress, existing methods often suffer from significant identity distortion under large facial pose variations or facial occlusions. In this paper, we propose FaithfulFaces, a pose-faithful facial identity preservation learning framework to improve IPT2V in complex dynamic scenes. The key of FaithfulFaces is a pose-shared identity aligner that refines and aligns facial poses across distinct views via a pose-shared dictionary and a pose variation-identity invariance constraint. By mapping single-view inputs into a global facial pose representation with explicit Euler angle embeddings, FaithfulFaces provides a pose-faithful facial prior that guides generative foundations toward robust identity-preserving generation. In particular, we develop a specialized pipeline to curate a high-quality video dataset featuring substantial facial pose diversity. Extensive experiments demonstrate that FaithfulFaces achieves state-of-the-art performance, maintaining superior identity consistency and structural clarity even as pose changes and occlusions occur.
Community
Pose-Faithful Facial Identity Preservation for Text-to-Video Generation
Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.
Tap or paste here to upload images
Cite arxiv.org/abs/2605.04702 in a model README.md to link it from this page.
Cite arxiv.org/abs/2605.04702 in a dataset README.md to link it from this page.
Cite arxiv.org/abs/2605.04702 in a Space README.md to link it from this page.
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.