Stable Signer: Hierarchical Sign Language Generative Model
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908801504903168 |
|---|---|
| author | Fang, Sen Feng, Yalin Zhong, Hongbin Zhang, Yanxin Metaxas, Dimitris N. |
| author_facet | Fang, Sen Feng, Yalin Zhong, Hongbin Zhang, Yanxin Metaxas, Dimitris N. |
| contents | Sign Language Production (SLP) is the process of converting the complex input text into a real video. Most previous works focused on the Text2Gloss, Gloss2Pose, Pose2Vid stages, and some concentrated on Prompt2Gloss and Text2Avatar stages. However, this field has made slow progress due to the inaccuracy of text conversion, pose generation, and the rendering of poses into real human videos in these stages, resulting in gradually accumulating errors. Therefore, in this paper, we streamline the traditional redundant structure, simplify and optimize the task objective, and design a new sign language generative model called Stable Signer. It redefines the SLP task as a hierarchical generation end-to-end task that only includes text understanding (Prompt2Gloss, Text2Gloss) and Pose2Vid, and executes text understanding through our proposed new Sign Language Understanding Linker called SLUL, and generates hand gestures through the named SLP-MoE hand gesture rendering expert block to end-to-end generate high-quality and multi-style sign language videos. SLUL is trained using the newly developed Semantic-Aware Gloss Masking Loss (SAGM Loss). Its performance has improved by 48.6% compared to the current SOTA generation methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_04048 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Stable Signer: Hierarchical Sign Language Generative Model Fang, Sen Feng, Yalin Zhong, Hongbin Zhang, Yanxin Metaxas, Dimitris N. Computer Vision and Pattern Recognition Computation and Language Computers and Society Sign Language Production (SLP) is the process of converting the complex input text into a real video. Most previous works focused on the Text2Gloss, Gloss2Pose, Pose2Vid stages, and some concentrated on Prompt2Gloss and Text2Avatar stages. However, this field has made slow progress due to the inaccuracy of text conversion, pose generation, and the rendering of poses into real human videos in these stages, resulting in gradually accumulating errors. Therefore, in this paper, we streamline the traditional redundant structure, simplify and optimize the task objective, and design a new sign language generative model called Stable Signer. It redefines the SLP task as a hierarchical generation end-to-end task that only includes text understanding (Prompt2Gloss, Text2Gloss) and Pose2Vid, and executes text understanding through our proposed new Sign Language Understanding Linker called SLUL, and generates hand gestures through the named SLP-MoE hand gesture rendering expert block to end-to-end generate high-quality and multi-style sign language videos. SLUL is trained using the newly developed Semantic-Aware Gloss Masking Loss (SAGM Loss). Its performance has improved by 48.6% compared to the current SOTA generation methods. |
| title | Stable Signer: Hierarchical Sign Language Generative Model |
| topic | Computer Vision and Pattern Recognition Computation and Language Computers and Society |
| url | https://arxiv.org/abs/2512.04048 |