Tamaththul3D creates high-fidelity 3D Saudi Sign Language avatars from video

Researchers have developed Tamaththul3D, a novel pipeline for generating high-fidelity 3D avatars of Saudi Sign Language (SSL). This system addresses a significant gap in resources for Arabic Sign Language (ArSL), which is used by approximately 400 million speakers. The project also introduces the first high-quality 3D parametric annotations for the Ishara-500 SSL dataset, featuring precise SMPL-X parameters for 500 distinct signs. Tamaththul3D integrates several tools, including SMPLer-X, WiLoR, and MediaPipe, to achieve state-of-the-art accuracy in hand and body pose reconstruction for ArSL. AI

影响 Establishes a framework for ArSL avatar reconstruction, potentially enabling new accessibility technologies and cultural preservation for the Arab Deaf community.

排序理由 Academic paper introducing a new method and dataset for 3D avatar reconstruction of sign language. [lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CV 阅读 →

• Ishara-500
• MediaPipe
• Saudi Sign Language
• SMPLer-X
• SMPL-X
• Tamaththul3D
• Arabic Sign Language

• 论文
• 其他

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →