Thabo Beeler

papers

875

total citations

papers (18)

ETH-XGaze: A Large Scale Dataset for Gaze Estimation under Extreme Head Pose and Gaze Variation

ECCV 2020arXiv

316

citations

Learning Personalized High Quality Volumetric Head Avatars From Monocular RGB Videos

CVPR 2023arXiv

citations

PhysAvatar: Learning the Physics of Dressed 3D Avatars from Visual Observations

ECCV 2024arXiv

citations

VariTex: Variational Neural Face Textures

ICCV 2021arXiv

citations

Preface: A Data-driven Volumetric Prior for Few-shot Ultra High-resolution Face Synthesis

ICCV 2023arXiv

citations

Spectral Graphormer: Spectral Graph-Based Transformer for Egocentric Two-Hand Reconstruction using Multi-View Color Images

ICCV 2023arXiv

citations

Gaussian Eigen Models for Human Heads

CVPR 2025arXiv

citations

BimArt: A Unified Approach for the Synthesis of 3D Bimanual Interaction with Articulated Objects

CVPR 2025arXiv

citations

Synthetic Prior for Few-Shot Drivable Head Avatar Inversion

CVPR 2025arXiv

citations

Ego4o: Egocentric Human Motion Capture and Understanding from Multi-Modal Input

CVPR 2025arXiv

citations

GroomLight: Hybrid Inverse Rendering for Relightable Human Hair Appearance Modeling

CVPR 2025arXiv

citations

FRAME: Floor-aligned Representation for Avatar Motion from Egocentric Video

CVPR 2025arXiv

citations

Attention-Driven Cropping for Very High Resolution Facial Landmark Detection

CVPR 2020

citations

REWIND: Real-Time Egocentric Whole-Body Motion Diffusion with Exemplar-Based Identity Conditioning

CVPR 2024

citations

Thabo Beeler

papers (18)

ETH-XGaze: A Large Scale Dataset for Gaze Estimation under Extreme Head Pose and Gaze Variation

Synthesizing Diverse Human Motions in 3D Indoor Scenes

Compositional Human-Scene Interaction Synthesis with Semantic Control

ITI-GEN: Inclusive Text-to-Image Generation

Optimizing Diffusion Noise Can Serve As Universal Motion Priors

Learning Personalized High Quality Volumetric Head Avatars From Monocular RGB Videos

PhysAvatar: Learning the Physics of Dressed 3D Avatars from Visual Observations

VariTex: Variational Neural Face Textures

Preface: A Data-driven Volumetric Prior for Few-shot Ultra High-resolution Face Synthesis

Spectral Graphormer: Spectral Graph-Based Transformer for Egocentric Two-Hand Reconstruction using Multi-View Color Images

Gaussian Eigen Models for Human Heads

BimArt: A Unified Approach for the Synthesis of 3D Bimanual Interaction with Articulated Objects

Synthetic Prior for Few-Shot Drivable Head Avatar Inversion

Ego4o: Egocentric Human Motion Capture and Understanding from Multi-Modal Input

GroomLight: Hybrid Inverse Rendering for Relightable Human Hair Appearance Modeling

FRAME: Floor-aligned Representation for Avatar Motion from Egocentric Video

Attention-Driven Cropping for Very High Resolution Facial Landmark Detection

REWIND: Real-Time Egocentric Whole-Body Motion Diffusion with Exemplar-Based Identity Conditioning

papers (18)

ETH-XGaze: A Large Scale Dataset for Gaze Estimation under Extreme Head Pose and Gaze Variation

Synthesizing Diverse Human Motions in 3D Indoor Scenes

Compositional Human-Scene Interaction Synthesis with Semantic Control

ITI-GEN: Inclusive Text-to-Image Generation

Optimizing Diffusion Noise Can Serve As Universal Motion Priors

Learning Personalized High Quality Volumetric Head Avatars From Monocular RGB Videos

PhysAvatar: Learning the Physics of Dressed 3D Avatars from Visual Observations

VariTex: Variational Neural Face Textures

Preface: A Data-driven Volumetric Prior for Few-shot Ultra High-resolution Face Synthesis

Spectral Graphormer: Spectral Graph-Based Transformer for Egocentric Two-Hand Reconstruction using Multi-View Color Images

Gaussian Eigen Models for Human Heads

BimArt: A Unified Approach for the Synthesis of 3D Bimanual Interaction with Articulated Objects

Synthetic Prior for Few-Shot Drivable Head Avatar Inversion

Ego4o: Egocentric Human Motion Capture and Understanding from Multi-Modal Input

GroomLight: Hybrid Inverse Rendering for Relightable Human Hair Appearance Modeling

FRAME: Floor-aligned Representation for Avatar Motion from Egocentric Video

Attention-Driven Cropping for Very High Resolution Facial Landmark Detection

REWIND: Real-Time Egocentric Whole-Body Motion Diffusion with Exemplar-Based Identity Conditioning