Salvato in:
| Autori principali: | , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2603.27915 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911552501710848 |
|---|---|
| author | Zhang, Liuzhou Zhang, Zeyu Wu, Biao Tang, Luyao Song, Zirui He, Hongyang Han, Renda Yao, Guangzhen Wang, Huacan Chen, Ronghao Chen, Xiuying Huang, Guan Zhu, Zheng |
| author_facet | Zhang, Liuzhou Zhang, Zeyu Wu, Biao Tang, Luyao Song, Zirui He, Hongyang Han, Renda Yao, Guangzhen Wang, Huacan Chen, Ronghao Chen, Xiuying Huang, Guan Zhu, Zheng |
| contents | Sign language plays a crucial role in bridging communication gaps between the deaf and hard-of-hearing communities. However, existing sign language video generation models often rely on complex intermediate representations, which limits their flexibility and efficiency. In this work, we propose a novel pose-free framework for real-time sign language video generation. Our method eliminates the need for intermediate pose representations by directly mapping natural language text to sign language videos using a diffusion-based approach. We introduce two key innovations: (1) a pose-free generative model based on the a state-of-the-art diffusion backbone, which learns implicit text-to-gesture alignments without pose estimation, and (2) a Trainable Sliding Tile Attention (T-STA) mechanism that accelerates inference by exploiting spatio-temporal locality patterns. Unlike previous training-free sparsity approaches, T-STA integrates trainable sparsity into both training and inference, ensuring consistency and eliminating the train-test gap. This approach significantly reduces computational overhead while maintaining high generation quality, making real-time deployment feasible. Our method increases video generation speed by 3.07x without compromising video quality. Our contributions open new avenues for real-time, high-quality, pose-free sign language synthesis, with potential applications in inclusive communication tools for diverse communities. Code: https://github.com/AIGeeksGroup/FlashSign. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_27915 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FlashSign: Pose-Free Guidance for Efficient Sign Language Video Generation Zhang, Liuzhou Zhang, Zeyu Wu, Biao Tang, Luyao Song, Zirui He, Hongyang Han, Renda Yao, Guangzhen Wang, Huacan Chen, Ronghao Chen, Xiuying Huang, Guan Zhu, Zheng Computer Vision and Pattern Recognition Sign language plays a crucial role in bridging communication gaps between the deaf and hard-of-hearing communities. However, existing sign language video generation models often rely on complex intermediate representations, which limits their flexibility and efficiency. In this work, we propose a novel pose-free framework for real-time sign language video generation. Our method eliminates the need for intermediate pose representations by directly mapping natural language text to sign language videos using a diffusion-based approach. We introduce two key innovations: (1) a pose-free generative model based on the a state-of-the-art diffusion backbone, which learns implicit text-to-gesture alignments without pose estimation, and (2) a Trainable Sliding Tile Attention (T-STA) mechanism that accelerates inference by exploiting spatio-temporal locality patterns. Unlike previous training-free sparsity approaches, T-STA integrates trainable sparsity into both training and inference, ensuring consistency and eliminating the train-test gap. This approach significantly reduces computational overhead while maintaining high generation quality, making real-time deployment feasible. Our method increases video generation speed by 3.07x without compromising video quality. Our contributions open new avenues for real-time, high-quality, pose-free sign language synthesis, with potential applications in inclusive communication tools for diverse communities. Code: https://github.com/AIGeeksGroup/FlashSign. |
| title | FlashSign: Pose-Free Guidance for Efficient Sign Language Video Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.27915 |