Skip to content

Latest commit

 

History

History
44 lines (31 loc) · 4.66 KB

README.md

File metadata and controls

44 lines (31 loc) · 4.66 KB
Raw

GCA (AAAI'2020)

Natural Image Matting via Guided Contextual Attention

Abstract

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 this http URL benchmark dataset demonstrate that our method outperforms state-of-the-art approaches in natural image matting.

Results and models

Method SAD MSE GRAD CONN Download
baseline (paper) 40.62 0.0106 21.53 38.43 -
GCA (paper) 35.28 0.0091 16.92 32.53 -
baseline (our) 36.50 0.0090 17.40 34.33 model | log
GCA (our) 34.77 0.0080 16.33 32.20 model | log

More results

Method SAD MSE GRAD CONN Download
baseline (with DIM pipeline) 49.95 0.0144 30.21 49.67 model | log
GCA (with DIM pipeline) 49.42 0.0129 28.07 49.47 model | log

Citation

@inproceedings{li2020natural,
  title={Natural Image Matting via Guided Contextual Attention},
  author={Li, Yaoyi and Lu, Hongtao},
  booktitle={Association for the Advancement of Artificial Intelligence (AAAI)},
  year={2020}
}