Scene Understanding

This Page is Under Construction, and the content below is obsolete.

3DunderstandV1In this theme we develop efficient inference techniques for 3D Scene understanding. Our ultimate goal is to take a few RGB(D) images and output in real-time the full scene-graph, with all objects present in the scene, their corresponding attributes and their 3D spatial relationship, e.g. “object A is supported by object B”. While this is very hot research area with many ongoing efforts, we currently focus on few research directions. These are in particular: 3D Pose estimation of known object instances or classes and semantic segmentation of (stereo) images.

Running Projects:

Selected Publications:

Datasets: