2 papers
cs.RO2026
EgoSpot:Egocentric Multimodal Control for Hands-Free Mobile Manipulation
Ganlin Zhang, Deheng Zhang, Longteng Duan +5
We propose a novel hands-free control framework for the Boston Dynamics Spot robot using the Microsoft HoloLens 2 mixed-reality headset. Enabling accessible robot control is critic…
cs.CV2025
MoGA: 3D Generative Avatar Prior for Monocular Gaussian Avatar Reconstruction
Zijian Dong, Longteng Duan, Jie Song +2
We present MoGA, a novel method to reconstruct high-fidelity 3D Gaussian avatars from a single-view image. The main challenge lies in inferring unseen appearance and geometric deta…