YCB-M: A Multi-Camera RGB-D Dataset for Object Recognition and 6DoF Pose Estimation
This dataset addresses the lack of multi-camera benchmarks for object recognition and 6DoF pose estimation, enabling researchers to compare cameras and improve algorithm robustness, though it is incremental as it extends existing YCB datasets.
The authors introduced YCB-M, a multi-camera RGB-D dataset with 49,294 frames from 7 different 3D cameras across 32 scenes, to evaluate pose estimation algorithms' sensitivity to camera specifics and enable robust algorithm development. They provided full ground truth 6DoF poses, segmentation, and other annotations for 20 YCB objects, along with an initial evaluation using a state-of-the-art system.
While a great variety of 3D cameras have been introduced in recent years, most publicly available datasets for object recognition and pose estimation focus on one single camera. In this work, we present a dataset of 32 scenes that have been captured by 7 different 3D cameras, totaling 49,294 frames. This allows evaluating the sensitivity of pose estimation algorithms to the specifics of the used camera and the development of more robust algorithms that are more independent of the camera model. Vice versa, our dataset enables researchers to perform a quantitative comparison of the data from several different cameras and depth sensing technologies and evaluate their algorithms before selecting a camera for their specific task. The scenes in our dataset contain 20 different objects from the common benchmark YCB object and model set [1], [2]. We provide full ground truth 6DoF poses for each object, per-pixel segmentation, 2D and 3D bounding boxes and a measure of the amount of occlusion of each object. We have also performed an initial evaluation of the cameras using our dataset on a state-of-the-art object recognition and pose estimation system [3].