Zhuang, L., Fan, S., Ru, Y., Audonnet, F., Henderson, P. and Aragon-Camarasa, G. (2025) Flat'n'Fold: A Diverse Multi-Modal Dataset for Garment Perception and Manipulation. [Data Collection]

Not all data is available to download from this page. Usually this is because the dataset is too large or it is restricted in some way.

Collection description

Flat'n'Fold is a large-scale dataset designed for garment manipulation, consisting of 1,212 human and 887 robot demonstrations of flattening and folding 44 unique garments across 8 categories. It provides comprehensive data, including synchronized multi-view RGB-D images, point clouds, and human and robot action data, capturing the entire manipulation process from crumpled to folded states.
The data file associated with this dataset is too large for standard download (~2TB). Please use the request data button to arrange alternative access. This dataset is licensed with a Creative Commons Attribution CC-BY 4.0 license.

Repository Staff Only: Update this record