← ArchivePaper2026
Step2Motion: Locomotion Reconstruction from Pressure Sensing Insoles
Jose Luis Ponton, Eduardo Alvarado, Lin Geng Foo, Nuria Pelechano, Carlos Andujar, Marc Habermann
Reconstructs full body locomotion from insoles carrying an IMU and sixteen pressure sensors, free of line of sight limits and unconstrained by a mocap suit.
How to read this
- Category
- Academic paper on full body motion reconstruction from a sparse wearable sensor
- Contributions
- First approach to reconstruct human locomotion from multi modal insole sensors, using both pressure and inertial signals
- Works from insoles carrying an IMU and sixteen pressure sensors per foot, so the whole capture rig fits inside a shoe
- Avoids the two classic constraints of other systems: no line of sight requirement as with optical capture, and no suit as with inertial mocap, which makes outdoor capture practical
- Evaluated across a range of locomotion styles including walking, jogging, moving sideways, tiptoeing, crouching and dancing
- Context
- This belongs to the sparse sensor motion reconstruction line, where the goal is to recover a full body pose from far less data than a mocap stage provides. It is a collaboration between the Universitat Politecnica de Catalunya group and the Max Planck Institute for Informatics, and its novelty is the choice of sensor: feet rather than the torso and limb IMUs that sparse inertial methods usually rely on.
- Correctness
- The claims rest on evaluation across a spread of locomotion styles, which is the right test for a method whose whole premise is generalising beyond a plain walk cycle. Note the scope, this reconstructs locomotion specifically, so upper body motion that does not register through the feet is inherently outside what the signal can carry.
- Clarity
- A clearly written Eurographics paper with a concrete hardware story, readable by a technical animator without a deep machine learning background.
- How to read it
- First pass, read the abstract and the hardware figure to understand exactly what signal the insoles provide. Second pass, study the reconstruction network and the evaluation across locomotion styles, since the interesting question is where the pressure signal stops being informative. Third pass is for anyone considering wearable capture on set, where the practical detail about outdoor and unconstrained use is the real payload.
This page summarises the entry and links to its original source. The archive never hosts or redistributes the publication itself.Show it in the full archive list →