Tuesday, November 29, 2011

Compressed-Sensing Recovery of Images and Video Using Multihypothesis Predictions

Some of you may have noticed my preference for featuring papers with code implementations earlier in the week. Well the trend continues with Compressed-Sensing Recovery of Images and Video Using Multihypothesis Predictions by Chen Chen, Eric W. Tramel and James E. Fowler. The abstract reads:

Compressed-sensing reconstruction of still images and video sequences driven by multihypothesis predictions is considered. Specifically, for still images, multiple predictions drawn for an image block are made from spatially surrounding blocks within an initial non-predicted reconstruction. For video, multihypothesis predictions of the current frame are generated from one or more previously reconstructed reference frames. In each case, the predictions are used to generate a residual in the domain of the compressed-sensing random projections. This residual being typically more compressible than the original signal leads to improved reconstruction quality. To appropriately weight the hypothesis predictions, a Tikhonov regularization to an ill-posed least-squares optimization is proposed. Experimental results demonstrate that the proposed reconstructions outperform alternative strategies not employing multihypothesis predictions.
The extended results page is here and the implementation featured in the paper is here.

Image Credit: NASA/JPL/Space Science Institute, N00178529.jpg was taken on November 27, 2011 and received on Earth November 28, 2011. The camera was pointing toward TITAN at approximately 748,439 kilometers away, and the image was taken using the CL1 and CB3 filters. This image has not been validated or calibrated.

No comments: