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

被引：1

作者：

Dai, Linhui ^{[1
]}

Song, Xiang ^{[1
]}

Liu, Xiaohong ^{[2
]}

Li, Chengqi ^{[1
]}

Shi, Zhihao ^{[1
]}

Chen, Jun ^{[1
]}

Brooks, Martin ^{[3
]}

机构：

[1] McMaster Univ, Dept Elect & Comp Engn, Hamilton, ON L8S 4K1, Canada

[2] Shanghai Jiao Tong Univ, John Hopcroft Ctr, Shanghai 200240, Peoples R China

[3] ShapeVis Inc, Ottawa, ON K2P 0A4, Canada

来源：

IEEE TRANSACTIONS ON MULTIMEDIA | 2023年 / 25卷

基金：

加拿大自然科学与工程研究理事会;

关键词：

Image matting; joint-task learning; frequency-guided attention; ATTENTION;

D O I：

10.1109/TMM.2022.3183403

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

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.

引用

页码：4868 / 4879

页数：12