Abstract
Most text-to-3D avatar generation methods assume normative body structures and cannot represent limb differences or amputations. DreamAble introduced 3D avatar generation with upper limb differences but did not address their animation. This paper extends DreamAble to animation by incorporating adapted skeletal structures into conventional rigging and motion retargeting pipelines. Motion sequences from actors with normative body structures are retargeted to 3D avatars with upper limb differences. Our findings advance inclusive 3D avatar animation, with potential applications in gaming, social virtual reality, and medical training environments.
Funding Information
  • Ministry of Trade, Industry and Energy (20023347)
  • Conselho Nacional de Desenvolvimento Científico e Tecnológico-CNPq (302259/2026-0)