It's more than a dream! Animatable #avatars from a single image are becoming a reality.
Watch the talk (in thread) to understand how we approach this in three steps: Dream, Lift, Animate.
Accepted to @3DVconf
Training 3D-aware face models just got easier! We're extending Cafca with FLAME parameters. 1.7M synthetic face images that are now plug-and-play ready with poses, shape, and expression coefficients.
🔗 Check out our brand-new dataset page: syntec-research.github.io/Cafca/cafca_da…
A purely synthetic face prior can generalize to casual in-the-wild captures and stylized faces 🤯
I'm happy to share our @SIGGRAPHAsia paper “Cafca: High-quality Novel View Synthesis of Expressive Faces from Casual Few-shot Captures.”
syntec-research.github.io/Cafca/
I will be presenting the WildGaussians paper this afternoon at @NeurIPSConf . To learn more about our paper, visit me at poster stand #1307 in East Exhibit Hall 16:30-19:30
A model that generates hand-object interactions based on text prompts!
I'm happy to share our @SIGGRAPHAsiapaper “DiffH2O: Diffusion-Based Synthesis of Hand-Object Interactions from Textual Descriptions”.
diffh2o.github.io
Yesterday, we presented Cafca---our latest work on casual few-shot face captures---at @SIGGRAPHAsia in Tokyo.
Check out our talk:
youtu.be/soNSzodOUvs
We release a dataset of 1.7 Mio. multi-view, multi-environment, multi-expression face images for research.
