Boosting General Trimap-free Matting in the Real-World Image

TL;DR

This paper introduces MFC-Net, a novel trimap-free image matting method that leverages salient object detection, along with a large real-world dataset, to improve accuracy and reduce domain shift in practical applications.

Contribution

The paper proposes a multi-feature fusion network for trimap-free matting, redefines foreground as salient objects, and creates the largest real-world matting dataset to date.

Findings

Significant improvement on synthetic and real-world images.

Outperforms existing trimap-free matting methods.

Establishes a large-scale real-world matting dataset.

Abstract

Image matting aims to obtain an alpha matte that separates foreground objects from the background accurately. Recently, trimap-free matting has been well studied because it requires only the original image without any extra input. Such methods usually extract a rough foreground by itself to take place trimap as further guidance. However, the definition of 'foreground' lacks a unified standard and thus ambiguities arise. Besides, the extracted foreground is sometimes incomplete due to inadequate network design. Most importantly, there is not a large-scale real-world matting dataset, and current trimap-free methods trained with synthetic images suffer from large domain shift problems in practice. In this paper, we define the salient object as foreground, which is consistent with human cognition and annotations of the current matting dataset. Meanwhile, data and technologies in salient object detection can be transferred to matting in a breeze. To obtain a more accurate and complete alpha matte, we propose a network called \textbf{M}ulti-\textbf{F}eature fusion-based \textbf{C}oarse-to-fine Network \textbf{(MFC-Net)}, which fully integrates multiple features for an accurate and complete alpha matte. Furthermore, we introduce image harmony in data composition to bridge the gap between synthetic and real images. More importantly, we establish the largest general matting dataset \textbf{(Real-19k)} in the real world to date. Experiments show that our method is significantly effective on both synthetic and real-world images, and the performance in the real-world dataset is far better than existing matting-free methods. Our code and data will be released soon.