arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.17020cs.CV
收藏

基于Trimap生成网络和轻量级非局部注意力的语义引导自然图像自动抠图

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

McGill University(麦吉尔大学);The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳));Shenzhen Institute of Artificial Intelligence and Robotics for Society(深圳人工智能与机器人学会)

Yuhongze Zhou, Liguang Zhou, Tin Lun Lam, Yangsheng Xu

摘要:

自然图像抠图的目的是使用alpha抠图精确地将前景对象从背景中分离出来。没有外部注释的全自动自然图像抠图是具有挑战性的。性能良好的抠图方法通常需要精确的劳动密集型手工制作的三分图作为额外的输入,而扩张前景分割的自动三分图生成方法的性能随着分割质量而波动。因此,我们认为,如何处理额外的信息输入的权衡是自动抠图的一个主要问题。本文提出了一种基于语义引导的自然图像自动抠图流水线,该流水线采用Trimap生成网络和轻量级非局部注意力,不需要输入Trimap和背景。具体来说,在前景分割的指导下,Trimap生成网络估计准确的trimap。然后,以估计的trimap为指导,我们的轻量级Non-local Matting Network with Refinement产生最终的alpha Matte,其trimap引导的全局聚合注意力块配备了步幅下采样卷积,降低了计算复杂度并提高了性能。实验结果表明,我们的抠图算法具有竞争力的性能与国家的最先进的方法在两个trimap自由和trimap需要方面。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑