New Models and Methods for Matting and Compositing

GrabCut is perhaps the most powerful semi-automatic algorithm for matting presented to date. In its existing form, it is not suitable for video object segmentation. This paper considers major extensions that make it suitable for this purpose. A method for initialising matting without user intervention is presented, followed by a more robust data model using a Mean Shift algorithm to control mod...

In this paper, we formulate interactive image matting as a constrained optimization problem. We first make some simple and reasonable assumptions about the alpha matte and assume that, geometrically, the closer two pixels are, the more likely they will have similar alpha values, conversely, the farther apart two pixels are, the more likely they will have different alpha values; photometrically,...

This paper addresses the problem of transparent object matting. Existing image matting approaches for transparent objects often require tedious capturing procedures and long processing time, which limit their practical use. In this paper, we first formulate transparent object matting as a refractive flow estimation problem. We then propose a deep learning framework, called TOM-Net, for learning...

Automatic human matting is highly desired for many real applications. We investigate recent methods and show that common bad cases happen when semantic segmentation fails. This indicates understanding crucial robust matting. From this, we develop a fast yet accurate framework, named Semantic Guided Human Matting (SGHM). It builds on network introduces light-weight module with only marginal comp...

Image matting is a fundamental technique used to extract fine foreground image from given by estimating the opacity values of each pixel. It one key techniques in processing and has wide range applications practical scenarios, such as video editing. Deep learning demonstrated outstanding performance various tasks, making it popular research topic. In recent years, methods based on deep have gai...