Cascade Image Matting with Deformable Graph Refinement

TL;DR

This paper introduces a cascade neural network with deformable graph refinement for precise human image matting, achieving state-of-the-art results by capturing global and local details efficiently.

Contribution

It proposes a novel cascade architecture combined with a deformable graph neural network module to improve fine detail extraction in image matting.

Findings

Achieves state-of-the-art performance on synthetic datasets.

Produces high-quality alpha mattes on real human images.

Reduces computational complexity of graph refinement.

Abstract

Image matting refers to the estimation of the opacity of foreground objects. It requires correct contours and fine details of foreground objects for the matting results. To better accomplish human image matting tasks, we propose the Cascade Image Matting Network with Deformable Graph Refinement, which can automatically predict precise alpha mattes from single human images without any additional inputs. We adopt a network cascade architecture to perform matting from low-to-high resolution, which corresponds to coarse-to-fine optimization. We also introduce the Deformable Graph Refinement (DGR) module based on graph neural networks (GNNs) to overcome the limitations of convolutional neural networks (CNNs). The DGR module can effectively capture long-range relations and obtain more global and local information to help produce finer alpha mattes. We also reduce the computation complexity of the DGR module by dynamically predicting the neighbors and apply DGR module to higher--resolution features. Experimental results demonstrate the ability of our CasDGR to achieve state-of-the-art performance on synthetic datasets and produce good results on real human images.