Tracking cloth deformation | Franco Coltraro

Video summary of the dataset.

Summary

We present a cloth dataset consisting of 120 high-quality recordings of several textiles during dynamic motions. Using a Motion Capture System, we record the location of key-points on the cloth surface of four types of fabrics (cotton, denim, wool and polyester) of two sizes and at different speeds. The scenarios considered are all dynamic and involve rapid shaking and twisting of the textiles, collisions with frictional objects, strong hits with a long rigid object and even self-collisions. For more details see (Coltraro et al., 2025) or follow this link.

Dataset

Click here to download the zip file or go to zenodo.

References

2025

Tracking cloth deformation: a novel dataset for closing the sim-to-real gap for robotic cloth manipulation learning

Franco Coltraro, Júlia Borràs , Maria Alberich-Carramiñana , and 1 more author

The International Journal of Robotics Research, 2025

Bib HTML PDF

@article{DatasetIJRR,
  title = {Tracking cloth deformation: a novel dataset for closing the sim-to-real gap for robotic cloth manipulation learning},
  author = {Coltraro, Franco and Borràs, Júlia and Alberich-Carramiñana, Maria and Torras, Carme},
  year = {2025},
  journal = {The International Journal of Robotics Research},
  doi = {https://doi.org/10.1177/02783649251317617},
}