2 papers
cs.CV2026
LiftAvatar: Kinematic-Space Completion for Expression-Controlled 3D Gaussian Avatar Animation
Hualiang Wei, Shunran Jia, Jialun Liu +1
We present LiftAvatar, a new paradigm that completes sparse monocular observations in kinematic space (e.g., facial expressions and head pose) and uses the completed signals to dri…
cs.CV2024
PRG: Prompt-Based Distillation Without Annotation via Proxy Relational Graph
Yijin Xu, Jialun Liu, Hualiang Wei +1
In this paper, we propose a new distillation method for extracting knowledge from Large Foundation Models (LFM) into lightweight models, introducing a novel supervision mode that d…