Object Pose Estimation Database

This database contains 16 objects, each sampled at 5^o angle increments along two rotational axes. All objects are available both with a black background, and with a cluttered background. Some of the objects are available in different lighting conditions (left, right, ambient). The montage below shows one view each for the objects.

The image below shows a subset of the available views.

Take me to the datasets

Associated Publication

If you use this database in a publication, you should reference the paper:

F. Viksten, P.-E. Forssén, B. Johansson, and A. Moe. Comparison of Local Image Descriptors for Full 6 Degree-of-Freedom Pose Estimation. IEEE International Conference on Robotics and Automation, May 2009. [BibTeX].

Other Related Publications

• F. Viksten and R. Söderberg and K. Nordberg and C. Perwass, Increasing Pose Estimation Performance using Multi-cue Integration ICRA 2006

• P-E. Forssén and A. Moe, Autonomous Learning of Object Appearances using Colour Contour Frames CRV 2006

• B. Johansson and A. Moe, Patch-Duplets for Object Recognition and Pose Estimation CRV 2005

• R. Söderberg, K. Nordberg, G.H. Granlund, An Invariant and Compact Representation for Unrestricted Pose Estimation IbPRIA 2005

• F. Viksten, A. Moe, Local Single-Patch Features for Pose Estimation Using the Log-Polar Transform IbPRIA 2005

• G.H. Granlund, A. Moe, Unrestricted Recognition of 3-D Objects for Robotics Using Multi-Level Triplet Invariants AI Magazine 2004