Issue No. 03 - March (2011 vol. 33)
Scott McCloskey , McGill University, Montreal
Michael Langer , McGill University, Montreal
Kaleem Siddiqi , McGill University, Montreal
This paper examines large partial occlusions in an image which occur near depth discontinuities when the foreground object is severely out of focus. We model these partial occlusions using matting, with the alpha value determined by the convolution of the blur kernel with a pinhole projection of the occluder. The main contribution is a method for removing the image contribution of the foreground occluder in regions of partial occlusion, which improves the visibility of the background scene. The method consists of three steps. First, the region of complete occlusion is estimated using a curve evolution method. Second, the alpha value at each pixel in the partly occluded region is estimated. Third, the intensity contribution of the foreground occluder is removed in regions of partial occlusion. Experiments demonstrate the method's ability to remove the effects of partial occlusion in single images with minimal user input.
Focus, matting, partial occlusion, curve evolution.
Scott McCloskey, Michael Langer, Kaleem Siddiqi, "Removal of Partial Occlusion from Single Images", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 33, no. , pp. 647-654, March 2011, doi:10.1109/TPAMI.2010.187