High-quality reconstruction of controllable 3D head avatars from 2D vide...
Supervised keypoint localization methods rely on large manually labeled ...
We present a novel algorithm to reduce tensor compute required by a
cond...
We present a novel method for multi image domain and multi-landmark
defi...
Grapheme-to-Phoneme (G2P) models convert words to their phonetic
pronunc...
We propose a general purpose approach to detect landmarks with improved
...
Neural sequence-to-sequence text-to-speech synthesis (TTS), such as
Taco...
We present a differentiable ray-tracing based novel face reconstruction
...
StyleGAN generates photorealistic portrait images of faces with eyes, te...
We present a novel strategy to automatically reconstruct 3D faces from
m...
Monocular image-based 3D reconstruction of faces is a long-standing prob...
Extreme deformation can drastically morph a structure from one structura...