The Character Technology Blog

The Character Technology Blog

Home
Notes
Archive
About

June 2025

May 2025

Today in Character Technology - 5.30.25
Nvidia brings temporally consistent human geo from video, mask-guided co-speech gestures, pose-guided animation for complex motions, and more!
 • 
Josh DiCarlo
Today in Character Technology - 5.28.25
Tencent drops a Video Avatar Competitor, Relightable Gaussian Avatars with Novel View Synthesis, Consistent Gaussian Head Model Synthesis, Better Lip…
 • 
Josh DiCarlo
Today in Character Technology - 5.22.25
Towards broader applications of 4D with Expressive Virtual Avatars from Multi-view Videos, Co-speech Gesture Synthesis with intentionality, Decoupled…
 • 
Josh DiCarlo
Today in Character Technology - 5.21.25
Multi-Character Interaction Synthesis, Facial Reaction Diffusion, and a Comprehensive AI-Driven framework for game asset creation from Tencent.
 • 
Josh DiCarlo
Today in Character Technology - 5.20.25
Hold for Google, Please. Aronofsky jumps on Deep Mind's AI bandwagon. Eurographics 2025.
 • 
Josh DiCarlo
Today in Character Technology - 5.19.25
Emotive Robots, Contrastive Language-Image Pretraining Distillation for Motion Synthesis, 3D Human Pose Estimation Benchmarking, and realtime image…
 • 
Josh DiCarlo
Today in Character Technology - 5.16.25
Long-term Dyadic Human Motion Synthesis, Stylized Gaussian Blendshapes, VR-sketches to 3D Garments, and 4D Motion Tokenization
 • 
Josh DiCarlo
Today in Character Technology - 5.15.25
More Cloth, Gaussians, and Text-to-3D!
 • 
Josh DiCarlo
Today in Character Technology - 5.14.25
Simulating Knots, Heterogeneous motion transfer, and more human gesture prediction.
 • 
Josh DiCarlo
© 2025 Josh DiCarlo
Privacy ∙ Terms ∙ Collection notice
Start writingGet the app
Substack is the home for great culture