Björn Stenger

I am a research scientist at the Rakuten Institute of Technology, where I work on computer vision and machine learning. My current work is on 3D reconstruction, visual search, image super-resolution, and video understanding.

Prior to Rakuten I worked at Toshiba Research (research page). I completed my PhD in computer vision at the University of Cambridge in Roberto Cipolla's group, co-supervised by Prof. Philip Torr. My Diplom in Computer Science is from the University of Bonn. During my studies, I spent time at the University of Victoria, at Hewlett-Packard, and at Siemens Corporate Research.

[E-mail]     [Scholar]     [BibTeX file]     [All Publications]

News

2017/10 - Welcome Bhaskar Rao from IIT Bombay!

2017/09 - Associate Editor of IEICE Trans. Information and Systems, special issue on Machine Vision and its Applications

Recent Work

ByNet-SR: Image Super Resolution with a Bypass Connection Network
J. Xu, Y. Chae, B. Stenger,
ICIP, September 2017.

New CNN architecture for image super-resolution with excellent quality/speed trade-off.

BigHand2.2M Benchmark: Hand Pose Data Set and State of the Art Analysis
S. Yuan, Q. Ye, B. Stenger, S. Jain, T.-K. Kim,
CVPR, July 2017.
[arxiv]

A new large dataset of depth maps with annotated 3D hand joints using a magnetic tracking system. The data is also used in the Hands in the Million Challenge.

Parsing Floor Plan Images
S. Dodge, J. Xu, B. Stenger,
MVA, May 2017.
[R-FP dataset coming soon][video coming soon]

Wall segmentation using fully convolutional networks (FCN) and applications in furniture fitting and 3D modeling.

Pano2CAD: Room Layout From A Single Panorama Image
J. Xu, B. Stenger, T. Kerola, T. Tung,
WACV, March 2017.
[arxiv]

Estimation of 3D room geometry from a single panorama image using surface normal estimation, 2D object detection and 3D object pose estimation.


website template credit