Robust Human Matting via Semantic Guidance
This provides a practical solution for human matting applications by reducing labeling costs and leveraging widely available segmentation data, though it is incremental as it builds on existing segmentation networks.
The paper tackles the problem of robust human matting by addressing failures in semantic human segmentation, developing a framework that uses a semantic segmentation network and a light-weight matting module to achieve high-quality results with minimal data. It shows that trained with only 200 matting images, the method outperforms recent methods on multiple benchmarks while remaining efficient.
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.