Motion from Blur

Supported in part by NSF and DARPA

Motion blur retains some information about motion, based on which motion may be recovered from blurred images. This is a difficult problem, as the situations of motion blur can be quite complicated, such as they may be space variant, nonlinear, and local. This paper addresses a very challenging problem: can we recover motion blindly from a single motion-blurred image?

There are mainly three contributions in our work

Fig. 1: Illustration of the motion blur constraint.

  1. Shengyang Dai and Ying Wu, "Motion from Blur", IEEE Conference on Computer Vision and Pattern Recognition (CVPR'08), Anchorage, Alaska, USA, June 24-26, 2008. (Oral) [Slides]
  2. Shengyang Dai and Ying Wu, "Estimating Space-variant Motion Blur without Deblurring", IEEE Conference on Image Processing (ICIP'08), San Diego, California, USA, October 12-15, 2008. (Oral)
  3. Shengyang Dai, Ming Yang, Ying Wu, and Aggelos K.Katsaggelos, "Tracking Motion-blurred Targets in Video", IEEE Conference on Image Processing (ICIP'06), Atlanta, Georgia, USA, October 8-11, 2006.


Space-variant motion estimation




Blur / Motion synthesis



Space-variant motion deblurring


Return to Research

Updated 9/2008. Copyright © 2006-2008 Ying Wu