Multi-scale Information Assembly for Image Matting

TL;DR

This paper introduces MSIA-matte, a multi-scale information assembly framework that leverages different levels of foreground information to produce high-quality image mattes from single RGB images, achieving state-of-the-art results.

Contribution

The paper proposes a novel multi-scale information assembly framework that combines advanced semantics and CNN features for improved image matting performance.

Findings

Achieves state-of-the-art performance on image matting benchmarks.

Effectively combines multi-scale foreground information.

Demonstrates robustness across diverse images.

Abstract

Image matting is a long-standing problem in computer graphics and vision, mostly identified as the accurate estimation of the foreground in input images. We argue that the foreground objects can be represented by different-level information, including the central bodies, large-grained boundaries, refined details, etc. Based on this observation, in this paper, we propose a multi-scale information assembly framework (MSIA-matte) to pull out high-quality alpha mattes from single RGB images. Technically speaking, given an input image, we extract advanced semantics as our subject content and retain initial CNN features to encode different-level foreground expression, then combine them by our well-designed information assembly strategy. Extensive experiments can prove the effectiveness of the proposed MSIA-matte, and we can achieve state-of-the-art performance compared to most existing matting networks.