Wider and Higher: Intensive Integration and Global Foreground Perception for Image Matting

TL;DR

This paper introduces the I2GFP network for image matting, emphasizing high-resolution features and global foreground perception, leading to state-of-the-art results by integrating wider and higher feature streams.

Contribution

The paper proposes a novel I2GFP network that enhances image matting by focusing on high-resolution features and global foreground perception, moving beyond traditional encoder-decoder architectures.

Findings

Achieves state-of-the-art performance on public datasets.

Demonstrates the effectiveness of wider and higher feature integration.

Shows that high-resolution features improve matting accuracy.

Abstract

This paper reviews recent deep-learning-based matting research and conceives our wider and higher motivation for image matting. Many approaches achieve alpha mattes with complex encoders to extract robust semantics, then resort to the U-net-like decoder to concatenate or fuse encoder features. However, image matting is essentially a pixel-wise regression, and the ideal situation is to perceive the maximum opacity correspondence from the input image. In this paper, we argue that the high-resolution feature representation, perception and communication are more crucial for matting accuracy. Therefore, we propose an Intensive Integration and Global Foreground Perception network (I2GFP) to integrate wider and higher feature streams. Wider means we combine intensive features in each decoder stage, while higher suggests we retain high-resolution intermediate features and perceive large-scale foreground appearance. Our motivation sacrifices model depth for a significant performance promotion. We perform extensive experiments to prove the proposed I2GFP model, and state-of-the-art results can be achieved on different public datasets.