5 papers
Registration-Free Learnable Multi-View Capture of Faces in Dense Semantic Correspondence
Panagiotis P. Filntisis, George Retsinas, Radek DanÄÄek +3
Recent frameworks like ToFu and TEMPEH provide an automated alternative to classical registration pipelines by predicting 3D meshes in dense semantic correspondence directly from c…
Emotional Speech-driven 3D Body Animation via Disentangled Latent Diffusion
Kiran Chhatre, Radek DanÄÄek, Nikos Athanasiou +4
Existing methods for synthesizing 3D human gestures from speech have shown promising results, but they do not explicitly model the impact of emotions on the generated gestures. Ins…
CLUTCH: Contextualized Language model for Unlocking Text-Conditioned Hand motion modelling in the wild
Balamurugan Thambiraja, Omid Taheri, Radek Danecek +3
Hands play a central role in daily life, yet modeling natural hand motions remains underexplored. Existing methods that tackle text-to-hand-motion generation or hand animation capt…
Supervising 3D Talking Head Avatars with Analysis-by-Audio-Synthesis
Radek DanÄÄek, Carolin Schmitt, Senya Polikovsky +1
In order to be widely applicable, speech-driven 3D head avatars must articulate their lips in accordance with speech, while also conveying the appropriate emotions with dynamically…
SMIRK: 3D Facial Expressions through Analysis-by-Neural-Synthesis
George Retsinas, Panagiotis P. Filntisis, Radek Danecek +4
While existing methods for 3D face reconstruction from in-the-wild images excel at recovering the overall face shape, they commonly miss subtle, extreme, asymmetric, or rarely obse…