SIPLAB: Sensing, Interaction & Perception Lab

Scalable motion capture in the wild (ECCV '26) play distributed ego-exo human motion capture from head-mounted devices read more

Team SIPLAB meet the people in the lab read more

Retrofitting real-world objects with multi-touch sensing (SIGGRAPH '26) play generating surface-intrinsic curves optimized for capacitive sensing read more

Full-body tracking in the wild (CVPR '26) play sparse wearable IMUs and UWB ranging for mobile pose estimation read more

egocentric heart rate estimation (ICCV '25) play to benefit downstream tasks read more

Dexterous manipulation (ACM CHI '18) play through haptic feedback for remote control and Mixed Reality interaction read more

• EgoExoMoCap
• Team SIPLAB
• Capacitive Sensing on Real-World Objects
• Ultra Diffusion Poser
• egoPPG
• CLAW

The SIPLAB is a research lab at ETH Zürich working on egocentric perception, computational interaction, and behavioral AI. We advance mixed reality, robotics, and human-computer inter­action toward adaptive intelli­gence and human-aware systems. We are part of the Department of Computer Science and the AI Center.

egocentric perception motion tracking, action understanding, and planning

input decoding for adaptive systems user modeling for computational interaction

behavioral AI human affect, emotions, and traits via digital biomarkers