Enabling Trimap-Free Image Matting With a Frequency-Guided Saliency-Aware Network via Joint Learning

Linhui Dai, Xiang Song, Xiaohong Liu, Chengqi Li, Zhihao Shi, Jun Chen, Martin Brooks

Abstract

This paper presents a strategic approach to tackling trimap-free natural image matting. Specifically, to address the false detection issue of existing trimap-free matting algorithms when the foreground object is not uniquely defined, we design a novel tangled structure (TangleNet) to handle foreground detection and matting prediction simultaneously. TangleNet enables information exchange between foreground segmentation and alpha prediction, producing high-quality alpha mattes for the most salient foreground object based on RGB inputs alone. TangleNet boosts network performance with a frequency-guided attention mechanism utilizing wavelet data. Additionally, we pretrain for salient object detection to aid in the foreground segmentation. Experimental results demonstrate that TangleNet is on par with the state-of-the-art matting methods requiring additional inputs, and outperforms all previous trimap-free algorithms in terms of both qualitative and quantitative results.
BibTeX
@article{dai2023enabling,
  author = {Linhui Dai and Xiang Song and Xiaohong Liu and Chengqi Li and Zhihao Shi and Jun Chen and Martin Brooks},
  title = {{Enabling Trimap-Free Image Matting With a Frequency-Guided Saliency-Aware Network via Joint Learning}},
  journal = {IEEE Trans. Multimedia},
  year = {2023},
  url = {https://openreview.net/forum?id=vLVIFL0auA},
}

Loading related content...

Figure