A wavelet-based multi-level factorized blendshape representation with distillation achieves ultra-detailed animatable avatars at 2000X lower cost and 10X smaller size, running at 24 FPS natively on Meta Quest 3.
Animatable neural radiance fields for modeling dynamic human bodies
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
MUA: Mobile Ultra-detailed Animatable Avatars
A wavelet-based multi-level factorized blendshape representation with distillation achieves ultra-detailed animatable avatars at 2000X lower cost and 10X smaller size, running at 24 FPS natively on Meta Quest 3.