Images/video convey enormous information about the activities in the 3D scene, and provide many clues to recover the information that is lost in the imaging process. These clues, if found, can also be used to handle the image degradation and improve the image quality, which recovers the high-quality images. Through image/video analysis, the hidden information can be recovered, and the recovered information can also be used to synthesize new images. This research lies in the intersection of the traditional DSP-based image processing research and the developing field of computer vision and computer graphics.

[1]	Image Super-resolution from a Single Image
[2]	Motion from Blur: A Unified View

1. Shengyang Dai and Ying Wu, "Motion from Blur", in Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR'08), Anchorage, Alaska, June 2008.  
 
2. Shengyang Dai, Mei Han, Wei Xu, Ying Wu and Yihong Gong, "Soft Edge Smoothness Prior for Alpha Channel Super Resolution", in Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR'07), Minneapolis, MN, June 2007   [PDF]