Effective Eyebrow Matting with Domain Adaptation
| dc.contributor.author | Wang, Luyuan | en_US |
| dc.contributor.author | Zhang, Hanyuan | en_US |
| dc.contributor.author | Xiao, Qinjie | en_US |
| dc.contributor.author | Xu, Hao | en_US |
| dc.contributor.author | Shen, Chunhua | en_US |
| dc.contributor.author | Jin, Xiaogang | en_US |
| dc.contributor.editor | Umetani, Nobuyuki | en_US |
| dc.contributor.editor | Wojtan, Chris | en_US |
| dc.contributor.editor | Vouga, Etienne | en_US |
| dc.date.accessioned | 2022-10-04T06:41:21Z | |
| dc.date.available | 2022-10-04T06:41:21Z | |
| dc.date.issued | 2022 | |
| dc.description.abstract | We present the first synthetic eyebrow matting datasets and a domain adaptation eyebrow matting network for learning domain-robust feature representation using synthetic eyebrow matting data and unlabeled in-the-wild images with adversarial learning. Different from existing matting methods that may suffer from the lack of ground-truth matting datasets, which are typically labor-intensive to annotate or even worse, unable to obtain, we train the matting network in a semi-supervised manner using synthetic matting datasets instead of ground-truth matting data while achieving high-quality results. Specifically, we first generate a large-scale synthetic eyebrow matting dataset by rendering avatars and collect a real-world eyebrow image dataset while maximizing the data diversity as much as possible. Then, we use the synthetic eyebrow dataset to train a multi-task network, which consists of a regression task to estimate the eyebrow alpha mattes and an adversarial task to adapt the learned features from synthetic data to real data. As a result, our method can successfully train an eyebrow matting network using synthetic data without the need to label any real data. Our method can accurately extract eyebrow alpha mattes from in-the-wild images without any additional prior and achieves state-of-the-art eyebrow matting performance. Extensive experiments demonstrate the superior performance of our method with both qualitative and quantitative results. | en_US |
| dc.description.number | 7 | |
| dc.description.sectionheaders | Image Detection and Understanding | |
| dc.description.seriesinformation | Computer Graphics Forum | |
| dc.description.volume | 41 | |
| dc.identifier.doi | 10.1111/cgf.14682 | |
| dc.identifier.issn | 1467-8659 | |
| dc.identifier.pages | 347-358 | |
| dc.identifier.pages | 12 pages | |
| dc.identifier.uri | https://doi.org/10.1111/cgf.14682 | |
| dc.identifier.uri | https://diglib.eg.org:443/handle/10.1111/cgf14682 | |
| dc.publisher | The Eurographics Association and John Wiley & Sons Ltd. | en_US |
| dc.subject | CCS Concepts: Computing methodologies --> Image processing | |
| dc.subject | Computing methodologies | |
| dc.subject | Image processing | |
| dc.title | Effective Eyebrow Matting with Domain Adaptation | en_US |