Computational Photography and Videos

Overview

As getting cheaper and cheaper, cameras (either still image cameras or video camcorders) become more and more accessible. Therefore, computational photography and videos has been a hot research topic recently. We investigate methods to enhance photos or videos with hand-held cameras. When taking pictures with hand-held cameras, handshakes often result in annoying artifacts, such as blur in photographs and jitter in videos.

For the first problem, in CVPR 2009, we proposed a technique for reconstructing a high-quality high dynamic range (HDR) image from a set of differently exposed and possibly blurred images taken with a hand-held camera. To overcome the problem with blurred long-exposed photographs, we use Bayesian framework to formulate the problem and apply a maximum likelihood approach to iteratively perform blur kernel estimation, HDR image reconstruction and camera curve recovery. When convergence, we simultaneously obtain an HDR image with rich and clear structures, the camera response curve and blur kernels.

For the second problem, we have proposed a new approach for video stabilization by directly stabilizing a video without explicitly estimating camera motion. The method first extracts robust feature trajectories from the input video. Optimization is performed to find a set of transformations to smooth out these trajectories and stabilize the video. In addition, the optimization also considers quality of the stabilized video and selects a video with not only smooth camera motion but also less unfilled area after stabilization. This work is published in ICCV 2009.

We have also investigated methods to animate still pictures into video textures. The results was published in SIGGRAPH 2005.

Publications

Video Stabilization using Robust Feature Trajectories
Ken-Yi Lee, Yung-Yu Chuang, Bing-Yu Chen, Ming Ouhyoung
ICCV 2009
High Dynamic Range Image Reconstruction from Hand-held Cameras
Pei-Ying Lu, Tz-Huan Huang, Meng-Sung Wu, Yi-Ting Cheng, Yung-Yu Chuang
CVPR 2009
Animating Pictures with Stochastic Motion Textures
Yung-Yu Chuang, Dan B Goldman, Ke Colin Zheng, Brian Curless, David Salesin, Richard Szeliski
SIGGRAPH 2005

Support

This research is supported by:
cyy -a-t- csie.ntu.edu.tw