The RGB-D Scenes Dataset v2 consists of 14 scenes containing furniture (chair, coffee table, sofa, table) and a subset of the objects in the RGB-D Object Dataset (bowls, caps, cereal boxes, coffee mugs, and soda cans). Each scene is a point cloud created by aligning a set of video frames using Patch Volumes Mapping*. These 3D reconstructions and ground truth object annotations are exactly those used in our ICRA 2014 paper (see README).


Entire RGB-D Scenes Dataset v.2 (189 MB) - Aligned scene point clouds, ground truth annotations, and camera pose estimates from 3D scene reconstruction (5.5 GB) - All RGB and depth image frames

Trimble 3D Warehouse Objects (256 MB) - Point clouds of Trimble 3D Warehouse objects used for learning HMP3D features and classifiers in our ICRA 2014 paper, in PLY format (see README).

Software (72 KB) - MATLAB code written by Pascal Getreuer for reading and writing PLY files.

*Patch Volumes: Segmentation-based Consistent Mapping with RGB-D Cameras P. Henry, D. Fox, A. Bhowmik, R. Mongia, International Conference on 3D Vision (3DV), 2013.

Acknowledgements: Special thanks to Peter Henry for helping with the data collection and 3D reconstruction.