Marc Habermann

papers

2,286

total citations

papers (24)

Physical Inertial Poser (PIP): Physics-Aware Real-Time Human Motion Tracking From Sparse Inertial Sensors

CVPR 2022arXiv

217

citations

EventCap: Monocular 3D Capture of High-Speed Human Motions Using an Event Camera

CVPR 2020arXiv

119

citations

ASH: Animatable Gaussian Splats for Efficient and Photoreal Human Rendering

CVPR 2024arXiv

104

citations

Monocular Real-Time Full Body Capture With Inter-Part Correlations

CVPR 2021arXiv

citations

Neural Radiance Transfer Fields for Relightable Novel-View Synthesis with Global Illumination

ECCV 2022arXiv

citations

DELIFFAS: Deformable Light Fields for Fast Avatar Synthesis

NEURIPS 2023arXiv

citations

ConvoFusion: Multi-Modal Conversational Diffusion for Co-Speech Gesture Synthesis

CVPR 2024arXiv

citations

LiveHand: Real-time and Photorealistic Neural Hand Rendering

ICCV 2023arXiv

citations

Holoported Characters: Real-time Free-viewpoint Rendering of Humans from Sparse RGB Cameras

CVPR 2024arXiv

citations

Efficient and Differentiable Shadow Computation for Inverse Problems

ICCV 2021arXiv

citations

EasyHOI: Unleashing the Power of Large Models for Reconstructing Hand-Object Interactions in the Wild

CVPR 2025arXiv

citations

Surf-D: Generating High-Quality Surfaces of Arbitrary Topologies Using Diffusion Models

ECCV 2024arXiv

citations

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

CVPR 2025arXiv

citations

MetaCap: Meta-learning Priors from Multi-View Imagery for Sparse-view Human Performance Capture and Rendering

ECCV 2024arXiv

citations

Relightable Neural Actor with Intrinsic Decomposition and Pose Control

ECCV 2024arXiv

citations

RePerformer: Immersive Human-centric Volumetric Videos from Playback to Photoreal Reperformance

CVPR 2025arXiv

citations

VINECS: Video-based Neural Character Skinning

CVPR 2024arXiv

citations

Real-time Free-view Human Rendering from Sparse-view RGB Videos using Double Unprojected Textures

CVPR 2025arXiv

citations

Thin-Shell-SfT: Fine-Grained Monocular Non-rigid 3D Surface Tracking with Neural Deformation Fields

CVPR 2025arXiv

citations

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

CVPR 2025arXiv

citations

Marc Habermann

papers (24)

Wonder3D: Single Image to 3D using Cross-Domain Diffusion

NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstruction

DeepCap: Monocular Human Performance Capture Using Weak Supervision

Monocular Real-Time Hand Shape and Motion Capture Using Multi-Modal Data

Physical Inertial Poser (PIP): Physics-Aware Real-Time Human Motion Tracking From Sparse Inertial Sensors

EventCap: Monocular 3D Capture of High-Speed Human Motions Using an Event Camera

ASH: Animatable Gaussian Splats for Efficient and Photoreal Human Rendering

Monocular Real-Time Full Body Capture With Inter-Part Correlations

Neural Radiance Transfer Fields for Relightable Novel-View Synthesis with Global Illumination

DELIFFAS: Deformable Light Fields for Fast Avatar Synthesis

ConvoFusion: Multi-Modal Conversational Diffusion for Co-Speech Gesture Synthesis

LiveHand: Real-time and Photorealistic Neural Hand Rendering

Holoported Characters: Real-time Free-viewpoint Rendering of Humans from Sparse RGB Cameras

Efficient and Differentiable Shadow Computation for Inverse Problems

EasyHOI: Unleashing the Power of Large Models for Reconstructing Hand-Object Interactions in the Wild

Surf-D: Generating High-Quality Surfaces of Arbitrary Topologies Using Diffusion Models

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

MetaCap: Meta-learning Priors from Multi-View Imagery for Sparse-view Human Performance Capture and Rendering

Relightable Neural Actor with Intrinsic Decomposition and Pose Control

RePerformer: Immersive Human-centric Volumetric Videos from Playback to Photoreal Reperformance

VINECS: Video-based Neural Character Skinning

Real-time Free-view Human Rendering from Sparse-view RGB Videos using Double Unprojected Textures

Thin-Shell-SfT: Fine-Grained Monocular Non-rigid 3D Surface Tracking with Neural Deformation Fields

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

papers (24)

Wonder3D: Single Image to 3D using Cross-Domain Diffusion

NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstruction

DeepCap: Monocular Human Performance Capture Using Weak Supervision

Monocular Real-Time Hand Shape and Motion Capture Using Multi-Modal Data

Physical Inertial Poser (PIP): Physics-Aware Real-Time Human Motion Tracking From Sparse Inertial Sensors

EventCap: Monocular 3D Capture of High-Speed Human Motions Using an Event Camera

ASH: Animatable Gaussian Splats for Efficient and Photoreal Human Rendering

Monocular Real-Time Full Body Capture With Inter-Part Correlations

Neural Radiance Transfer Fields for Relightable Novel-View Synthesis with Global Illumination

DELIFFAS: Deformable Light Fields for Fast Avatar Synthesis

ConvoFusion: Multi-Modal Conversational Diffusion for Co-Speech Gesture Synthesis

LiveHand: Real-time and Photorealistic Neural Hand Rendering

Holoported Characters: Real-time Free-viewpoint Rendering of Humans from Sparse RGB Cameras

Efficient and Differentiable Shadow Computation for Inverse Problems

EasyHOI: Unleashing the Power of Large Models for Reconstructing Hand-Object Interactions in the Wild

Surf-D: Generating High-Quality Surfaces of Arbitrary Topologies Using Diffusion Models

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

MetaCap: Meta-learning Priors from Multi-View Imagery for Sparse-view Human Performance Capture and Rendering

Relightable Neural Actor with Intrinsic Decomposition and Pose Control

RePerformer: Immersive Human-centric Volumetric Videos from Playback to Photoreal Reperformance

VINECS: Video-based Neural Character Skinning

Real-time Free-view Human Rendering from Sparse-view RGB Videos using Double Unprojected Textures

Thin-Shell-SfT: Fine-Grained Monocular Non-rigid 3D Surface Tracking with Neural Deformation Fields

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