Affiliation:
1. The University of Sydney, Australia
2. JD Explore Academy, JD.com, China
Abstract
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. In this paper, we investigate the difficulties when extending them to natural images with salient transparent/meticulous foregrounds or non-salient foregrounds. To address the problem, a 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. Simultaneously, the learned semantic features guide the matting network to focus on the transition areas via an attention mechanism. We also construct a test set AIM-500 that contains 500 diverse natural images covering all types along with manually labeled alpha mattes, making it feasible to benchmark the generalization ability of AIM models. Results of the experiments demonstrate that our network trained on available composite matting datasets outperforms existing methods both objectively and subjectively. The source code and dataset are available at https://github.com/JizhiziLi/AIM.
Publisher
International Joint Conferences on Artificial Intelligence Organization
Cited by
26 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Text-Guided Portrait Image Matting;IEEE Transactions on Artificial Intelligence;2024-08
2. Real-Time Video Matting Based on RVM and Mobile ViT;IEICE Transactions on Information and Systems;2024-06-01
3. Color subspace exploring for natural image matting;IET Image Processing;2024-04-24
4. VMFormer: End-to-End Video Matting with Transformer;2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV);2024-01-03
5. LWGSS: Light-Weight Green Spill Suppression for Green Screen Matting;Lecture Notes in Computer Science;2024