Designing Effective Inter-Pixel Information Flow for Natural Image Matting

by   Yağız Aksoy, et al.

We present a novel, purely affinity-based natural image matting algorithm. Our method relies on carefully defined pixel-to-pixel connections that enable effective use of information available in the image. We control the information flow from the known-opacity regions into the unknown region, as well as within the unknown region itself, by utilizing multiple definitions of pixel affinities. Among other forms of information flow, we introduce color-mixture flow, which builds upon local linear embedding and effectively encapsulates the relation between different pixel opacities. Our resulting novel linear system formulation can be solved in closed-form and is robust against several fundamental challenges of natural matting such as holes and remote intricate structures. Our evaluation using the alpha matting benchmark suggests a significant performance improvement over the current methods. While our method is primarily designed as a standalone matting tool, we show that it can also be used for regularizing mattes obtained by sampling-based methods. We extend our formulation to layer color estimation and show that the use of multiple channels of flow increases the layer color quality. We also demonstrate our performance in green-screen keying and further analyze the characteristics of the affinities used in our method.


page 2

page 3

page 4

page 7

page 9

page 10

page 11

page 12


Fast color transfer from multiple images

Color transfer between images uses the statistics information of image e...

Secure Watermarking Scheme for Color Image Using Intensity of Pixel and LSB Substitution

In this paper a novel spatial domain LSB based watermarking scheme for c...

StainNet: a fast and robust stain normalization network

Pathological images may have large variabilities in color intensities du...

Sparse Coding for Alpha Matting

Existing color sampling based alpha matting methods use the compositing ...

Evaluating the weight sensitivity in AHP-based flood risk estimation models

In the analytic hierarchy process (AHP) based flood risk estimation mode...

Natural Image Matting via Guided Contextual Attention

Over the last few years, deep learning based approaches have achieved ou...

Towards building a Crowd-Sourced Sky Map

We describe a system that builds a high dynamic-range and wide-angle ima...

Please sign up or login with your details

Forgot password? Click here to reset