Ottersten, Björn[University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > >]
12-Jun-2015
IEEE Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'15), (Best paper award)
Yes
International
IEEE Conference on Computer Vision and Pattern Recognition Workshop (CVPRW), (Best paper award)
07-06-2015 to 12-06-2015
[en] Real-Time ; Non-Rigid Depth Video ; Multi-Frame Super Resolution
[en] This paper proposes to enhance low resolution dynamic depth videos containing freely non–rigidly moving objects with a new dynamic multi–frame super–resolution algorithm. Existent methods are either limited to rigid objects, or restricted to global lateral motions discarding radial displacements. We address these shortcomings by accounting for non–rigid displacements in 3D. In addition to 2D optical flow, we estimate the depth displacement, and simultaneously correct the depth measurement by Kalman filtering. This concept is incorporated efficiently in a multi–frame super–resolution framework. It is formulated in a recursive manner that ensures an efficient deployment in real–time. Results show the overall improved performance of the proposed method as compared to alternative approaches, and specifically in handling relatively large 3D motions. Test examples range from a full moving human body to a highly dynamic facial video with varying expressions.
SnT, Interdisciplinary Centre for Security, Reliability and Trust