Robust Human Matting via Semantic Guidance

TL;DR

This paper introduces a semantic-guided human matting framework that leverages semantic segmentation to improve robustness and efficiency, requiring minimal training data and outperforming existing methods on benchmarks.

Contribution

It proposes a novel, data-efficient human matting approach that combines semantic segmentation with a lightweight matting module, enhancing robustness and reducing data annotation costs.

Findings

Trained with only 200 images, the method generalizes well to real-world data.

Outperforms recent human matting methods on multiple benchmarks.

Maintains high accuracy with marginal computational overhead.

Abstract

Automatic human matting is highly desired for many real applications. We investigate recent human matting methods and show that common bad cases happen when semantic human segmentation fails. This indicates that semantic understanding is crucial for robust human matting. From this, we develop a fast yet accurate human matting framework, named Semantic Guided Human Matting (SGHM). It builds on a semantic human segmentation network and introduces a light-weight matting module with only marginal computational cost. Unlike previous works, our framework is data efficient, which requires a small amount of matting ground-truth to learn to estimate high quality object mattes. Our experiments show that trained with merely 200 matting images, our method can generalize well to real-world datasets, and outperform recent methods on multiple benchmarks, while remaining efficient. Considering the unbearable labeling cost of matting data and widely available segmentation data, our method becomes a practical and effective solution for the task of human matting. Source code is available at https://github.com/cxgincsu/SemanticGuidedHumanMatting.