Date: less than 1 minute read

HouseCat6D: A Large-Scale Multi-Modal Category Level 6D Object Perception Dataset with Household Objects in Realistic Scenarios

HyunJun Jung   Shun-Cheng Wu   Patrick Ruhkamp   Guangyao Zhai   Hannah Schieber   Giulia Rizzoli   Pengyuan Wang   Hongcheng Zhao   Lorenzo Garattoni   Sven Meier   Daniel Roth   Nassir Navab   Benjamin Busam  
Technical University of Munich   Toyota Motor Europe  




HouseCat6D is a category-level 6D object perception dataset with multi-modal RGB, depth, and polarimetric (RGBD+P) captures. It covers 194 diverse household objects across 10 categories, including photometrically challenging materials, with high-quality pose annotations, large-scale scenes, and dense robotic grasp labels. We also report benchmarks for leading category-level pose estimation methods.

Paper

@inproceedings{jung2024housecat6d,
  title={HouseCat6D - A Large-Scale Multi-Modal Category Level 6D Object Perception Dataset with Household Objects in Realistic Scenarios},
  author={Jung, HyunJun and Wu, Shun-Cheng and Ruhkamp, Patrick and Zhai, Guangyao and Schieber, Hannah and Rizzoli, Giulia and Wang, Pengyuan and Zhao, Hongcheng and Garattoni, Lorenzo and Meier, Sven and Roth, Daniel and Navab, Nassir and Busam, Benjamin},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  pages={22498--22508},
  year={2024}
}

Code

Dataset tools are available at Junggy/HouseCat6D.