Improving Deep Image Matting via Local Smoothness Assumption

TL;DR

This paper introduces a deep image matting method that leverages local smoothness assumptions, proposing three techniques to enhance model performance and outperform existing methods.

Contribution

It systematically incorporates local smoothness assumptions into deep learning for image matting, introducing training refinement, color augmentation, and backpropagating refinement.

Findings

Significant performance improvement over existing methods

Effective use of local smoothness assumptions in deep learning

Validated through comprehensive experiments

Abstract

Natural image matting is a fundamental and challenging computer vision task. Conventionally, the problem is formulated as an underconstrained problem. Since the problem is ill-posed, further assumptions on the data distribution are required to make the problem well-posed. For classical matting methods, a commonly adopted assumption is the local smoothness assumption on foreground and background colors. However, the use of such assumptions was not systematically considered for deep learning based matting methods. In this work, we consider two local smoothness assumptions which can help improving deep image matting models. Based on the local smoothness assumptions, we propose three techniques, i.e., training set refinement, color augmentation and backpropagating refinement, which can improve the performance of the deep image matting model significantly. We conduct experiments to examine the effectiveness of the proposed algorithm. The experimental results show that the proposed method has favorable performance compared with existing matting methods.