ContactDB is a household object contact image dataset. The dataset captures rich hand-object contacts that occur during grasping using a thermal camera. ContactDB includes 3750 3D meshes of 50 household objects with contact map textures and 375,000 frames of synchronized RGB-D+ thermal images.

Citation

@inproceedings{brahmbhatt2018contactdb,
title={{ContactDB: Analyzing and Predicting Grasp Contact via Thermal Imaging}},
author={Samarth Brahmbhatt and Cusuh Ham and Charles C. Kemp and James Hays},
booktitle={IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
year={2019},
note={\url{https://contactdb.cc.gatech.edu}}
}