Hugging Face Trending Papers

From Sign Language Generation to Humanoid Execution: Vision-Language Guided Retargeting with Collision Mitigation

Read the original on Hugging Face Trending Papers →

Recent sign language generation (SLG) systems increasingly output dense 3D body representations, which better preserve full-body kinematics and geometry for downstream embodiment on humanoid robots. However, these generated motions frequently exhibit self-intersections such as hand-hand and hand-torso penetration.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv AI
Jun 6

Tamaththul3D: High-Fidelity 3D Saudi Sign Language Avatars from Monocular Video

arXiv:2605. 05367v2 Announce Type: replace-cross Abstract: Existing 3D sign language avatar reconstruction methods are developed and evaluated exclusively on Western sign languages, and no 3D parametric annotations exist for any Arabic Sign Language dataset, a gap that blocks the development of avatar-based accessibility applications for the Arab Deaf community.

By Eyad Alghamdi, Sattam Altuuaim, Obay Ghulam, Abdulrahman Qutah, Yousef Basoodan