[go: up one dir, main page]
Institute Homepage
Institute Homepage Sign In
We combine research on computer vision, computer graphics, and machine learning to teach computers to see and understand humans and their behavior. By capturing 3D human behavior from video at scale, we train digital humans that behave like real humans.

Our research uses Computer Vision to learn digital humans that can perceive, learn, and act in virtual 3D worlds. This involves capturing the shape, appearance, and motion of real people as well as their interactions with each other and the 3D scene using monocular video. We leverage this to learn generative models of people and their behavior and evaluate these models by synthesizing realistic looking humans behaving in virtual worlds.

This work combines Computer Vision, Machine Learning, and Computer Graphics.

Director
Michael Black

Michael Black

Emeritus / Acting Director
Admin Team
Melanie Feldhofer

Melanie Feldhofer

Department Manager
Nicole Overbaugh

Nicole Overbaugh

Office Coordinator
+49 7071 601 1800
ps-admin@tuebingen.mpg.de

Perceiving Systems Highlights

Talk Perceiving Systems 2026-02-17

SAM3D Body

SAM3D Body
Talk Perceiving Systems 2026-02-12

Beyond the Scan: High-fidelity Human Digitalization at Scale

Beyond the Scan: High-fidelity Human Digitalization at Scale
Press Release Perceiving Systems 2026-02-11

Michael J. Black elected to the U.S. National Academy of Engineering

{"en"=>"Michael J. Black elected to the U.S. National Academy of Engineering", "de"=>"Michael J. Black elected to the U.S. National Academy of Engineering"}
Talk Perceiving Systems 2025-10-30

Text, Touch and Trajectories: Reconstructing 3D Humans with 3T’s

Text, Touch and Trajectories: Reconstructing 3D Humans with 3T’s
Conference Paper Haptic Intelligence Perceiving Systems 2025-10-01

Contact-Aware Refinement of Human Pose Pseudo-Ground Truth via Bioimpedance Sensing

Contact-Aware Refinement of Human Pose Pseudo-Ground Truth via Bioimpedance Sensing
Conference Paper Perceiving Systems 2025-10-01

Im2Haircut: Single-view Strand-based Hair Reconstruction for Human Avatars

{Im2Haircut:} Single-view Strand-based Hair Reconstruction for Human Avatars
Talk Perceiving Systems 2025-10-01

Decoding animal health: Computer vision approaches to motion and emotional states in animals

Decoding animal health: Computer vision approaches to motion and emotional states in animals
Talk Perceiving Systems 2025-07-24

Capturing Dexterity: Large-Scale Demonstration Acquisition and Dynamic Contact Modeling for Bimanual Hand–Object Interaction

Capturing Dexterity: Large-Scale Demonstration Acquisition and Dynamic Contact Modeling for Bimanual Hand–Object Interaction
Article Haptic Intelligence Perceiving Systems 2025-04-01

Wrist-to-Wrist Bioimpedance Can Reliably Detect Discrete Self-Touch

Wrist-to-Wrist Bioimpedance Can Reliably Detect Discrete Self-Touch IEEE Transactions on Instrumentation and Measurement
Talk Perceiving Systems 2025-03-10

How and what to film in virtual environments?

How and what to film in virtual environments?
Conference Paper Perceiving Systems 2025-03-01

CameraHMR: Aligning People with Perspective

{CameraHMR}: Aligning People with Perspective
Talk Perceiving Systems 2025-02-18

The Dawn of Video Generation: Preliminary Explorations with SORA-like Models

The Dawn of Video Generation: Preliminary Explorations with SORA-like Models
Talk Perceiving Systems 2025-02-06

Computer Vision at the Mirror Stage: Questioning and Refining Visual Categorization

Computer Vision at the Mirror Stage: Questioning and Refining Visual Categorization
Blog Post Perceiving Systems 2024-12-03

MoSh: Motion and Shape Capture in the Age of AI

{"en"=>"MoSh: Motion and Shape Capture in the Age of AI", "de"=>"MoSh: Motion and Shape Capture in the Age of AI"}
Article Perceiving Systems 2024-12-01

PuzzleAvatar: Assembling 3D Avatars from Personal Albums

{PuzzleAvatar}: Assembling {3D} Avatars from Personal Albums ACM Transactions on Graphics
Talk Perceiving Systems 2024-11-28

How to predict the inside from the outside? Segment, register, model and infer!

How to predict the inside from the outside? Segment, register, model and infer!
Blog Post Perceiving Systems 2024-11-08

Writing a good scientific paper

{"en"=>"Writing a good scientific paper", "de"=>"Writing a good scientific paper"}
Talk Perceiving Systems 2024-10-14

Diffusion Models for Human Motion Synthesis

Diffusion Models for Human Motion Synthesis
Talk Perceiving Systems 2024-10-10

Reconstruction and Animation of Realistic Head Avatars

Reconstruction and Animation of Realistic Head Avatars
Talk Perceiving Systems 2024-09-26

Collaborative Control for Geometry-Conditioned PBR Image Generation

Collaborative Control for Geometry-Conditioned PBR Image Generation
Talk Perceiving Systems 2024-09-26

Geometry Image Diffusion: Fast and Data-Efficient Text-to-3D with Image-Based Surface Representation

Geometry Image Diffusion: Fast and Data-Efficient Text-to-3D with Image-Based Surface Representation
Conference Paper Perceiving Systems 2024-09-16

HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Video

{HOLD}: Category-agnostic {3D} Reconstruction of Interacting Hands and Objects from Video
Conference Paper Perceiving Systems 2024-09-16

HIT: Estimating Internal Human Implicit Tissues from the Body Surface

{HIT}: Estimating Internal Human Implicit Tissues from the Body Surface
Conference Paper Perceiving Systems 2024-09-16

EMAGE: Towards Unified Holistic Co-Speech Gesture Generation via Expressive Masked Audio Gesture Modeling

{EMAGE}: Towards Unified Holistic Co-Speech Gesture Generation via Expressive Masked Audio Gesture Modeling
Conference Paper Perceiving Systems 2024-09-16

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

{WHAM}: Reconstructing World-grounded Humans with Accurate {3D} Motion
Conference Paper Perceiving Systems 2024-09-16

ChatPose: Chatting about 3D Human Pose

{ChatPose}: Chatting about 3D Human Pose
Conference Paper Perceiving Systems 2024-09-16

SCULPT: Shape-Conditioned Unpaired Learning of Pose-dependent Clothed and Textured Human Meshes

{SCULPT}: Shape-Conditioned Unpaired Learning of Pose-dependent Clothed and Textured Human Meshes
Conference Paper Perceiving Systems 2024-09-16

WANDR: Intention-guided Human Motion Generation

{WANDR}: Intention-guided Human Motion Generation