Semantic-guided Automatic Natural Image Matting with Trimap Generation Network and Light-weight Non-local Attention

TL;DR

This paper introduces a semantic-guided automatic image matting method that generates trimaps without external input, using a novel network with light-weight non-local attention to achieve competitive results.

Contribution

The paper proposes a trimap-free natural image matting pipeline with a Trimap Generation Network and a light-weight non-local attention network, improving automation and efficiency.

Findings

Achieves competitive performance with state-of-the-art methods.

Does not require external trimap or background input.

Reduces computational complexity while maintaining accuracy.

Abstract

Natural image matting aims to precisely separate foreground objects from background using alpha matte. Fully automatic natural image matting without external annotation is challenging. Well-performed matting methods usually require accurate labor-intensive handcrafted trimap as extra input, while the performance of automatic trimap generation method of dilating foreground segmentation fluctuates with segmentation quality. Therefore, we argue that how to handle trade-off of additional information input is a major issue in automatic matting. This paper presents a semantic-guided automatic natural image matting pipeline with Trimap Generation Network and light-weight non-local attention, which does not need trimap and background as input. Specifically, guided by foreground segmentation, Trimap Generation Network estimates accurate trimap. Then, with estimated trimap as guidance, our light-weight Non-local Matting Network with Refinement produces final alpha matte, whose trimap-guided global aggregation attention block is equipped with stride downsampling convolution, reducing computation complexity and promoting performance. Experimental results show that our matting algorithm has competitive performance with state-of-the-art methods in both trimap-free and trimap-needed aspects.