Semantic-guided Automatic Natural Image Matting with Light-weight Non-local Attention

Natural image matting aims to precisely separate foreground objects from background using alpha matte. Fully automatic natural image matting without external annotation is quite 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 universal semantic-guided automatic natural image matting pipeline with light-weight non-local attention without trimap and background image as input. Specifically, guided by semantic information of coarse foreground segmentation, Trimap Generation Network estimates accurate trimap. With estimated trimap and RGB image as input, 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 current state-of-the-art methods in both trimap-free and trimap-needed aspects.