Institute Homepage
Institute Homepage Sign In

Back

Research Overview

Inferring and exploiting contact

Generative Proxemics: A Prior for 3D Social Interaction from Images

BITE -- Dog Shape and Pose from an Image

HOLD -- inferring 3D hand and object shape from video

MOVER -- Reconstructing 3D Scenes and People using Interaction

Datasets for understanding humans and animals

The Poses for Equine Research Dataset (PFERD)

BEAT2 Dataset for Holistic Co-Speech Gesture Generation

ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulation

The BioAMASS Dataset

OpenCapBench dataset

Human health and the 3D body

Body Shape Models in Treating Anorexia Nervosa

Customized Bone Plants for Humerus Shaft Fractures

Reconstructing Signing Avatars From Video Using Linguistic Priors

The AI animator

HAAR: Text-Conditioned Generative Model of 3D Strand-based Human Hairstyles

Gaussian Garments

PuzzleAvatar: Assembling 3D Avatars from Personal Albums

FLARE: Fast Learning of Animatable and Relightable Mesh Avatars

Language, Vision, and World Models

AWOL: Analysis WithOut synthesis using Language

Re-Thinking Inverse Graphics with Large Language Models

TeCH: Text-guided Reconstruction of Clothed Humans

Human pose, shape, and motion capture

WHAM: Reconstructing World-grounded Humans with Accurate 3D Motion

3D Human Pose Estimation via Intuitive Physics

Accurate 3D Body Shape Regression using Metric and Semantic Attributes

BEV

Generating human motion

Generating Human Interaction Motions in Scenes with Text Control

TEMOS: Generating Diverse Human Motions from Text

EMAGE: Full-body Gestures from Audio

TEACH: Temporal Action Compositions for 3D Humans

Robot Perception Group

AirCap: 3D Motion Capture

AirCap: Perception-Based Control

Data Team

Lab Tours and Public Outreach

Collecting Data - From the Idea to the Publication

Capture Technologies Setup

Completed Projects

Clothing Capture and Modeling

Modeling Human Movement

/ps/projects/action-and-behavior

/ps/projects/inverse-graphics-proj

/ps/projects/image-segmentation-and-semantics

/ps/projects/groups-and-crowds

/ps/projects/learning-from-synthetic-data

/ps/projects/learning-high-dimensional-deep-representations

/ps/projects/efficient-and-scalable-inference

Hierarchical Graphs for Generalized Modelling of Clothing Dynamics

Learning to Resolve Intersections in Neural Multi-Garment Simulations

Reconstructing Simulation-Ready Clothing with Photo-Realistic Appearance from Multi-View Video

Text-Conditioned Generative Model of 3D Strand-based Human Hairstyles

Human Hair Reconstruction with Strand-Aligned 3D Gaussians

Joker: Conditional 3D Head Synthesis with Extreme Facial Expressions

Goal Driven Motion Generation

Perceiving Systems Members

Capture Technologies Setup

Capture Technologies Setup

Our unique capture technologies include 4D scanners, a motion capture system, multiple high-resolution video cameras, IMU sensors, pressure sensors, VR headsets, photo studio equipment and tools for accurate anthropometric measurements. For more information visit the Facilities section.

Our team is responsible for setting up, maintaining and reconfiguring the systems, as well as synchronizing multiple technologies. Members of the Data Team are trained to operate and maintain all scanners and other equipment.

Our Capture Hall is housing most of the equipment. The large capture hall (21m long, 14m wide and 8,5m high) allows full flexibility for our set ups. The capture hall includes a changing room, kitchen, clothes washing facilites, and a large storage area. Showers are also available nearby. Lighting conditions can be changed for different trials, varying from powerful LED lighting for high-speed recordings to total darkness.

Members

Perceiving Systems
Tsvetelina Alexiadis
Data Team Lead
Perceiving Systems
Markus Höschle
Mechatronics Technician
Perceiving Systems
Taylor Obersat
Data Collection and Processing Specialist
Perceiving Systems
Claudia Gallatz
Trial Coordinator