6-DoF SpatialBench

Paper_link: https://arxiv.org/abs/2502.13143
Project Page: https://qizekun.github.io/sofar/
Github Code: https://github.com/qizekun/SoFar

Previous spatial perception LLMs mainly focused on operations of positional relationships, such as left-right, near-far, size, and counting, etc. In actual object manipulation, the orientation of the object is also a very important factor. Therefore, we proposed a new 6-DoF spatial perception benchmark dataset for evaluating the model's reasoning capabilities in position, orientation, and position-orientation relationships. We evaluated existing spatial perception models on this benchmark dataset.

The evaluation baseline is SoFar, a 6-DoF system for spatial reasoning and robotic manipulation.

Download the images.zip and extract it to ./datasets/6dof_spatialbench/. The overall directory structure should be:

│SoFar/datasets/6dof_spatialbench/
├── spatial_data.json
└── images/
    ├── 0.png
    └── ...