RigidFusion Dataset

RGB-D Sequences:
The RGB-D sequences used in the paper are available as raw ROS bag files and as exported to colour and depth image pairs (RGBD_Export). This dataset is devided into two categroies. One is "camera_sequence", which we collected the data using RGB-D camera only. While the sequences collected via Ada robot belong to another category. The ground truth trajectories of camera optical frame and object are stored in "groundtruth_camera.txt" and "groundtruth_object.txt" files respectively. The "vicon_camera.txt" file stores the trajectory of vicon_makers on camera, and the extrinsc calibration between vicon makers and camera's optical frame  can be found in "/asus/handeye.txt". 

The format of RGB-D images is:
color images - 8 bit in PNG. Resolution: VGA
depth images - 16 bit monochrome in PNG, scaled by 1000. Resolution: VGA

Citation
If you use this dataset, please cite:
Long, Ran, et al. "RigidFusion: Robot localisation and mapping in environments with large dynamic rigid objects." IEEE Robotics and Automation Letters 6.2 (2021): 3703-3710.

The dataset is licensed under the Creative Commons BY-NC-SA. You may freely modify and distribute the dataset for non-commercial use given, that you acknowledge its source and use the same license.