Cut out soft foreground in natural image with deep learning
Cut out soft foreground in natural image with deep learning
Deep Automatic Natural Image Matting
arXiv paper abstract https://arxiv.org/abs/2107.07235v1
arXiv PDF paper https://arxiv.org/pdf/2107.07235v1.pdf
Image matting benchmark https://paperswithcode.com/sota/image-matting-on-aim-500
Automatic image matting (AIM) refers to estimating the soft foreground from an arbitrary natural image without any auxiliary input like trimap, which is useful for image editing.
Prior methods try to learn semantic features to aid the matting process while being limited to images with salient opaque foregrounds such as humans and animals.
... extending them to natural images with salient transparent/meticulous foregrounds or non-salient foregrounds.
... novel end-to-end matting network is proposed, which can predict a generalized trimap for any image of the above types as a unified semantic representation.
... learned semantic features guide the matting network to focus on the transition areas via an attention mechanism.
... test set AIM-500 that contains 500 diverse natural images covering all types along with manually labeled alpha mattes
... network ... outperforms existing methods both objectively and subjectively. ...
Please like and share this post if you enjoyed it using the buttons at the bottom!
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
Comments