Deep Learning for Semantic Scene Analysis

Scene understanding is a challenging topic in computer vision, robots and artificial intelligence. Given one or more images, we want to infer what type of scene is shown in the image, what objects are visible, and physical or contextual relations between the observed objects.

Deep learning has transformed the field of computer vision, and now rivals human-level performance in tasks such as image recognition and object detection. We exploit convolutional neural networks (CNNs) for solving challenging scene interpretation task.

Omid Hosseini, Oliver Groth, Alexander Kirillov, Michael Ying Yang and Carsten Rother.

Analyzing Modular CNN Architectures for Joint Depth Prediction and Semantic Segmentation.

In International Conference on Robotics and Automation (ICRA), 2017

Michael Ying Yang, Wentong Liao, Hanno Ackermann, and Bodo Rosenhahn.

On Support Relations and Semantic Scene Graphs.

Arxiv 1609.05834, 2016

Siva Mustikovela, Michael Ying Yang, and Carsten Rother.

Can Ground Truth Label Propagation from Video help Semantic Segmentation?

In ECCV Workshop on Video Segmentation, 2016

David Richmond, Dagmar Kainmueller, Michael Ying Yang, Gene Myers, and Carsten Rother.

Mapping Auto-context to a Deep, Sparse ConvNet for Semantic Segmentation.

In British Machine Vision Conference (BMVC), 2016

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