Adaptive Propagation-Based Color-Sampling for Alpha Matting

Abstract

Image matting refers to the problem of foreground extraction from an image and transparency determination of the pixels. Although other matting algorithms have been proposed, most are not sufficiently robust to obtain satisfactory matting results in different regions of an image, such as smooth regions, nonuniform color distribution regions and isolated color regions. This paper proposes a novel matting algorithm that can extract high-quality mattes from different regions of an image. Our proposed algorithm combines propagation and color-sampling methods. Unlike previous propagation-based approaches that use either local or nonlocal propagation methods, our propagation framework adaptively uses both local and nonlocal processes according to the detection results of the different regions in the image. Our color-sampling strategy, which is based on the characteristics of the superpixel, uses a simple sample selection criterion and requires significantly less computational cost than previous color-sampling methods. Experimental results show that our adaptive propagation framework, alone, outperforms the state-of-the-art propagation-based approaches. Combined with our color-sampling method, it can effectively handle different regions in the image and produce both visually and quantitatively high-quality matting results.