Data & Code Dataset access might require filling out a form and is subject to approval. Data is for research purposes only. Data X-Avatar: Expressive Human Avatars Hi4D: 4D Instance Segmentation of Close Human Interaction Learning Locally Editable Virtual Humans IM Avatar: Implicit Morphable Head Avatars from Videos EM-POSE: 3D Human Pose Estimation from Sparse Electromagnetic Trackers Towards End-to-end Video-based Eye-Tracking Hierarchical Reinforcement Learning Explains Task Interleaving Behavior Deep Inertial Poser: Learning to Reconstruct Human Pose from Sparse Inertial Measurements in Real Time Cross-modal deep variational hand pose estimation Duo-VIO: Fast, Light-weight, Stereo Inertial Odometry In-air Gestures Around Unmodified Mobile Devices Code X-Avatar: Expressive Human Avatars Vid2Avatar: 3D Avatar Reconstruction from Videos in the Wild via Self-supervised Scene Decomposition PointAvatar: Deformable Point-based Head Avatars from Videos HOOD: Hierarchical Graphs for Generalized Modelling of Clothing Dynamics Hi4D: 4D Instance Segmentation of Close Human Interaction HARP: Personalized Hand Reconstruction from a Monocular RGB Video Learning Locally Editable Virtual Humans ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulation InstantAvatar: Learning Avatars from Monocular Video in 60 Seconds TempCLR: Reconstructing Hands via Time-Coherent Contrastive Learning SFP: State-free Priors for Exploration in Off-Policy Reinforcement Learning gDNA: Towards Generative Detailed Neural Avatars D-Grasp: Physically Plausible Dynamic Grasp Synthesis for Hand-Object Interactions IM Avatar: Implicit Morphable Head Avatars from Videos Fast-SNARF: A Fast Deformer for Articulated Neural Fields A Spatio-temporal Transformer for 3D Human Motion Prediction Human Performance Capture from Monocular Video in the Wild Render In-between: Motion Guided Video Synthesis for Action Interpolation VariTex: Variational Neural Face Textures SNARF: Differentiable Forward Skinning for Animating Non-Rigid Neural Implicit Shapes PeCLR: Self-Supervised 3D Hand Pose Estimation from monocular RGB via Equivariant Contrastive Learning Shape-aware Multi-Person Pose Estimation from Multi-view Images EM-POSE: 3D Human Pose Estimation from Sparse Electromagnetic Trackers Improved Learning of Robot Manipulation Tasks via Tactile Intrinsic Motivation Learning Functionally Decomposed Hierarchies for Continuous Control Tasks With Path Planning CoSE: Compositional Stroke Embeddings Self-Learning Transformations for Improving Gaze and Head Redirection Convolutional Autoencoders for Human Motion Infilling Spatial Attention Improves Iterative 6D Object Pose Estimation ETH-XGaze: A Large Scale Dataset for Gaze Estimation under Extreme Head Pose and Gaze Variation Category Level Object Pose Estimation via Neural Analysis-by-Synthesis Human Body Model Fitting by Learned Gradient Descent Towards End-to-end Video-based Eye-Tracking Detecting Relevance during Decision-Making from Eye Movements for UI Adaptation Learning to Assemble: Estimating 6D Poses for Robotic Object-Object Manipulation Hierarchical Reinforcement Learning Explains Task Interleaving Behavior Content-Consistent Generation of Realistic Eyes with Style Structured Prediction Helps 3D Human Motion Modelling Photo-Realistic Monocular Gaze Redirection Using Generative Adversarial Networks Few-Shot Adaptive Gaze Estimation Monocular Neural Image Based Rendering with Continuous View Control Context-Aware Online Adaptation of Mixed Reality Interfaces Unpaired Pose Guided Human Image Generation Video-based Prediction of Hand-grasp Preshaping with Application to Prosthesis Control Demonstration-Guided Deep Reinforcement Learning of Control Policies for Dexterous Human-Robot Interaction STCN: Stochastic Temporal Convolutional Networks Deep Inertial Poser: Learning to Reconstruct Human Pose from Sparse Inertial Measurements in Real Time Deep Pictorial Gaze Estimation Cross-modal deep variational hand pose estimation Learning to Find Eye Region Landmarks for Remote Gaze Estimation in Unconstrained Settings DeepWriting: Making Digital Ink Editable via Deep Generative Modeling AdaM: Adapting Multi-User Interfaces for Collaborative Environments in Real-Time Plan3D: Viewpoint and Trajectory Optimization for Aerial Multi-View Stereo Reconstruction Learning human motion models for long-term predictions Guiding InfoGAN with Semi-Supervision Duo-VIO: Fast, Light-weight, Stereo Inertial Odometry