TransMatting: Enhancing Transparent Objects Matting with Transformers
Authors:
- Huanqia CaiHCHuanqia Cai
- Fanglei XueFXFanglei Xue
- Lele XuLXLele Xu
- Lili GuoLGLili Guo
Preprint
Abstract
Image matting refers to predicting the alpha values of unknown foreground areas from natural images. Prior methods have focused on propagating alpha values from known to unknown regions. However, not all natural images have a specifically known foreground. Images of transparent objects, like glass, smoke, web, etc., have less or no known foreground. In this paper, we propose a Transformer-based network, TransMatting, to model transparent objects with a big receptive field. Specifically, we redesign the trimap as three learnable tri-tokens for introducing advanced semantic features into the self-attention mechanism. A small convolutional network is proposed to utilize the global feature and non-background mask to guide the multi-scale feature propagation from encoder to decoder for maintaining the contexture of transparent objects. In addition, we create a high-resolution matting dataset of transparent objects with small known foreground areas. Experiments on several matting benchmarks demonstrate the superiority of our proposed method over the current state-of-the-art methods.Keywords
All Related Versions
This publication has 15 references indexed in Scilit:
- CrossFormer++: A Versatile Vision Transformer Hinging on Cross-Scale AttentionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2023
- Scalable Vision Transformers with Hierarchical Pooling2021
- Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformer2021
- Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers2021
- Deep Automatic Portrait Matting2016
- Microsoft COCO: Common Objects in Context2014
- KNN MattingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009
- Spectral MattingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2008
- A Closed-Form Solution to Natural Image MattingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2007