08:46
HQ3DAvatar: High Quality Controllable 3D Head Avatar, TOG 2024
00:58
Showcase of Holoported Characters (CVPR 2024): Real-time 3D Avatar of Christian Theobalt
06:05
VINECS: Video-based Neural Character Skinning. In CVPR, 2024
03:29
ASH: Animatable Gaussian Splats for Efficient and Photoreal Human Rendering. In CVPR, 2024
01:34
ConvoFusion: Multi-Modal Conversational Diffusion for Co-Speech Gesture Synthesis. In CVPR, 2024.
07:02
Egocentric Whole Body Motion Capture with FisheyeViT and Diffusion Based Motion Refinement.
07:48
3D Human Pose Perception from Egocentric Stereo Videos, In CVPR, 2024
09:07
EventEgo3D 3D Human Motion Capture from Egocentric Event Streams. In CVPR, 2024
07:55
Holoported Characters: Real-time Free-viewpoint Rendering of Humans from Sparse RGB Cameras.
05:13
ROAM: Robust and Object-aware Motion Generation using Neural Pose Descriptors, 3DV, 2024
04:38
SceNeRFlow: Time-Consistent Reconstruction of General Dynamic Scenes, 3DV, 2024
00:33
Our Neural Rendering technology applied to The Matrix 4 movie data.
04:10
Decaf: Monocular Deformation Capture for Face and Hand Interactions. In SIGGRAPH ASIA, 2023.
05:38
NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstruction. In ICCV, 2023.
03:19
LiveHand: Real-time and Photorealistic Neural Hand Rendering. In ICCV, 2023.
06:03
AvatarStudio: Text-driven Editing of 3D Dynamic Human Head Avatars. In SIGGRAPH ASIA 2023.
05:08
HDHumans: A Hybrid Approach for High-fidelity Digital Humans, In SCA, 2023
05:22
EgoLocate, In SIGGRAPH 2023.
01:03
Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold. SIGGRAPH 2023
04:09
General Neural Gauge Fields. In ICLR, 2023
07:21
IMoS Intent Driven Full Body Motion Synthesis for Human Object Interactions. In EUROGRAPHICS, 2023.
06:26
Scene Aware 3D Multi Human Motion Capture from a Single Camera. In EUROGRAPHICS, 2023
09:03
EventNeRF: Neural Radiance Fields from a Single Colour Event Camera. In CVPR, 2023.
06:51
MoFusion: A Framework for Denoising-Diffusion-based Motion Synthesis. In CVPR, 2023
05:54
Scene-aware Egocentric 3D Human Pose Estimation. In CVPR, 2023.
05:11
Estimating Egocentric 3D Human Pose in the Wild with External Weak Supervision. In CVPR, 2022.
05:45
φ-SfT: Shape-from-Template with a Physics-Based Deformation Model. In CVPR, 2022.
01:32:53
Advances in Neural Rendering - EUROGRAPHICS 2022 STAR Report
08:59
EventHands: Real-Time Neural 3D Hand Pose Estimation from an Event Stream. In ICCV, 2021
05:58
Gravity-Aware Monocular 3D Human-Object Reconstruction. In ICCV, 2021
09:06
High-Fidelity Neural Human Motion Transfer from Monocular Video. In CVPR, 2021
05:43
HumanGAN: A Generative Model of Humans Images. In 3DV, 2021
03:49
Learning Complete 3D Morphable Face Models from Images and Videos. In CVPR, 2021.
05:52
Learning Meaningful Controls for Fluids. In SIGGRAPH, 2021.
05:56
Monocular Real-time Full Body Capture with Inter-part Correlations. In CVPR, 2021
09:46
Neural Actor: Neural Free-view Synthesis of Human Actors with Pose Control. In SIGGRAPH Asia 2021
07:26
Non-Rigid Neural Radiance Fields. In ICCV, 2021
06:59
PhotoApp: Photorealistic Appearance Editing of Head Portraits. In SIGGRAPH, 2021
03:20
StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesis. In ICLR, 2021
09:37
StyleVideoGAN: A Temporal Generative Model using a Pretrained StyleGAN. In BMVC, 2021
01:35
VideoForensicsHQ: Detecting High-quality Manipulated Face Videos. In ICME, 2021
07:16
Estimating Egocentric 3D Human Pose in Global Space. ICCV 2021 (Oral).
02:03
Efficient and Differentiable Shadow Computation for Inverse Problems. In ICCV, 2021.
04:30
Deep Physics-aware Inference of Cloth Deformation for Monocular Human Performance Capture (3DV'21)
03:00
Differentiable Event Stream Simulator for Non-Rigid 3D Tracking. In CVPRW, 2021.
08:12
Real-time Deep Dynamic Characters (SIGGRAPH 2021)
06:59
Neural Monocular 3D Human Motion Capture With Physical Awareness (SIGGRAPH 2021)
06:30
Real-time Global Illumination Decomposition of Videos (ACM TOG 2021)
05:05
i3DMM: Deep Implicit 3D Morphable Model of Human Heads
08:23
Pose-Guided Human Animation from a Single Image in the Wild
09:52
Egocentric Videoconferencing (SIGGRAPH Asia 2020)
04:01
PIE: Portrait Image Embedding for Semantic Control (SIGGRAPH Asia 2020)
06:10
RGB2Hands: Real-Time Tracking of 3D Hand Interactions from Monocular RGB Video (SIGGRAPH Asia 2020)
07:10
Deep Relightable Textures: Volumetric Performance Capture with Neural Rendering (SIGGRAPH Asia 2020)
05:31
PhysCap:Physically Plausible Monocular 3D Motion Capture in Real Time (SIGGRAPH Asia 2020)
05:54
Neural Dense Non-Rigid Structure from Motion with Latent Space Constraints (ECCV 2020)
03:57
HTML: A Parametric Hand Texture Model for 3D Hand Reconstruction and Personalization (ECCV 2020)
06:18
Neural Sparse Voxel Fields (NeurIPS 2020)
05:10
A Method to Overcome Annotation Errors for Depth-Based Hand Pose Estimation (IEEE FG 2020)
03:50
Vid2Curve: Simultaneous Camera Motion Estimation and Thin Structure Reconstruction (SIGGRAPH 2020)
X
About
Christian Theobalt is a Professor of Computer Science and the Director of the Visual Computing and Artificial Intelligence Department at the Max-Planck-Institute for Informatics, Saarbruecken, Germany. He is also a Professor of Computer Science at Saarland University. Most of his research deals with algorithmic problems that lie at the intersection of Computer Graphics, Computer Vision, and Machine Learning such as dynamic 3D scene reconstruction and marker-less motion capture, virtual humans, computer animation, neural rendering and neural scene representations, computational videography, appearance and reflectance modelling, machine learning for graphics and vision, new sensors for 3D acquisition, advanced video processing, virtual and augmented reality, image- and physically-based rendering, as well as inverse rendering.
Tags