Object Pose Estimation in RGB(D) Images

This project addresses the problem of estimating the 6D Pose of specific objects from a single RGB(D) image. We present a flexible approach that can deal with generic objects, both textured and texture-less. We propose an approach that “learns to compare”. This is done by describing the posterior density of a particular object pose with a CNN - convolutional neural network that compares observed and rendered images.

Video

Related Publications

Eric Brachmann, Frank Michel, Alexander Krull, Michael Ying Yang, Stefan Gumhold, and Carsten Rother.

Uncertainty-driven 6D Pose Estimation of Objects and Scenes from a Single RGB Image.

In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016 [Code]

Alexander Krull, Eric Brachmann, Frank Michel, Michael Ying Yang, Stefan Gumhold, and Carsten Rother.

Learning analysis-by-synthesis for 6D pose estimation in RGB-D images.

In IEEE International Conference on Computer Vision (ICCV), 2015

Frank Michel, Alexander Krull, Eric Brachmann, Michael Ying Yang, Stefan Gumhold, and Carsten Rother.

Pose estimation of kinematic chain instances via object coordinate regression.

In British Machine Vision Conference (BMVC), 2015