TransMatting: Enhancing Transparent Objects Matting with Transformers

TL;DR

TransMatting introduces a Transformer-based approach for transparent object matting, leveraging a novel tri-token trimap representation and global feature guidance, achieving superior results on benchmark datasets.

Contribution

The paper presents a new Transformer architecture with tri-token trimaps and a global feature-guided propagation method for transparent object matting.

Findings

Outperforms current state-of-the-art methods on benchmark datasets.

Introduces a high-resolution transparent object matting dataset.

Demonstrates effectiveness of tri-token trimaps and global feature guidance.

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.