Natural Image Matting via Guided Contextual Attention

13 Jan 2020  ·  Yaoyi Li, Hongtao Lu ·

Over the last few years, deep learning based approaches have achieved outstanding improvements in natural image matting. Many of these methods can generate visually plausible alpha estimations, but typically yield blurry structures or textures in the semitransparent area. This is due to the local ambiguity of transparent objects. One possible solution is to leverage the far-surrounding information to estimate the local opacity. Traditional affinity-based methods often suffer from the high computational complexity, which are not suitable for high resolution alpha estimation. Inspired by affinity-based method and the successes of contextual attention in inpainting, we develop a novel end-to-end approach for natural image matting with a guided contextual attention module, which is specifically designed for image matting. Guided contextual attention module directly propagates high-level opacity information globally based on the learned low-level affinity. The proposed method can mimic information flow of affinity-based methods and utilize rich features learned by deep neural networks simultaneously. Experiment results on Composition-1k testing set and benchmark dataset demonstrate that our method outperforms state-of-the-art approaches in natural image matting. Code and models are available at

PDF Abstract


Results from Other Papers

Task Dataset Model Metric Name Metric Value Rank Source Paper Compare
Semantic Image Matting Semantic Image Matting Dataset GCA SAD 39.28 # 2
MSE(10^3) 11.0 # 2
Grad 28.70 # 2
Conn 36.03 # 2


No methods listed for this paper. Add relevant methods here