Semantic-guided Automatic Natural Image Matting with Trimap Generation Network and Light-weight Non-local Attention
This addresses the challenge of reducing manual effort in image matting for applications like photo editing, though it is incremental as it builds on existing segmentation and attention techniques.
The paper tackles the problem of fully automatic natural image matting without requiring external annotations like trimaps, by proposing a pipeline that uses a Trimap Generation Network guided by foreground segmentation and a light-weight non-local attention network, achieving competitive performance with state-of-the-art methods.
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.