Abstract

We present a new image matting algorithm to extract con- sistent alpha mattes across sub-images of a light field image. Instead of matting each sub-image individually, our approach utilizes the epipo- lar plane image (EPI) to construct comprehensive foreground and back- ground sample sets across the sub-images without missing a true sample. The sample sets represent all color variation of foreground and back- ground in a light field image, and the optimal alpha matte is obtained by choosing the best combination of foreground and background samples that minimizes the linear composite error sub ject to the EPI correspon- dence constraint. To further preserve consistency of the estimated alpha mattes across different sub-images, we impose a smoothness constraint along the EPI of alpha mattes. In experimental evaluations, we have cre- ated a dataset where the ground truth alpha mattes of light field images were obtained by using the blue screen technique. A variety of exper- iments show that our proposed algorithm produces both visually and quantitatively high-quality matting results for light field images.