Javier Romero

15

Papers

76

Total Citations

Papers (15)

From Audio to Photoreal Embodiment: Synthesizing Humans in Conversations

ATLAS: Decoupling Skeletal and Shape Parameters for Expressive Parametric Human Modeling

FRESA: Feedforward Reconstruction of Personalized Skinned Avatars from Few Images

Learning From Synthetic Humans

On Human Motion Prediction Using Recurrent Neural Networks

Unite the People: Closing the Loop Between 3D and 2D Human Representations

Dynamic FAUST: Registering Human Bodies in Motion

Detailed Full-Body Reconstructions of Moving People From Monocular RGB-D Sequences

A Simple yet Effective Baseline for 3D Human Pose Estimation

Efficient Learning on Point Clouds With Basis Point Sets

FACSIMILE: Fast and Accurate Scans From an Image in Less Than a Second

Learning Realistic Human Reposing Using Cyclic Self-Supervision With 3D Shape, Pose, and Appearance Consistency

AutoAvatar: Autoregressive Neural Fields for Dynamic Avatar Modeling

Avat3r: Large Animatable Gaussian Reconstruction Model for High-fidelity 3D Head Avatars

URHand: Universal Relightable Hands