تقرير
Joint Face Image Restoration and Frontalization for Recognition
| العنوان: | Joint Face Image Restoration and Frontalization for Recognition |
|---|---|
| المؤلفون: | Tu, Xiaoguang, Zhao, Jian, Liu, Qiankun, Ai, Wenjie, Guo, Guodong, Li, Zhifeng, Liu, Wei, Feng, Jiashi |
| سنة النشر: | 2021 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Computer Vision and Pattern Recognition |
| الوصف: | In real-world scenarios, many factors may harm face recognition performance, e.g., large pose, bad illumination,low resolution, blur and noise. To address these challenges, previous efforts usually first restore the low-quality faces to high-quality ones and then perform face recognition. However, most of these methods are stage-wise, which is sub-optimal and deviates from the reality. In this paper, we address all these challenges jointly for unconstrained face recognition. We propose an Multi-Degradation Face Restoration (MDFR) model to restore frontalized high-quality faces from the given low-quality ones under arbitrary facial poses, with three distinct novelties. First, MDFR is a well-designed encoder-decoder architecture which extracts feature representation from an input face image with arbitrary low-quality factors and restores it to a high-quality counterpart. Second, MDFR introduces a pose residual learning strategy along with a 3D-based Pose Normalization Module (PNM), which can perceive the pose gap between the input initial pose and its real-frontal pose to guide the face frontalization. Finally, MDFR can generate frontalized high-quality face images by a single unified network, showing a strong capability of preserving face identity. Qualitative and quantitative experiments on both controlled and in-the-wild benchmarks demonstrate the superiority of MDFR over state-of-the-art methods on both face frontalization and face restoration. Comment: 14 pages, 9 figures |
| نوع الوثيقة: | Working Paper |
| DOI: | 10.1109/TCSVT.2021.3078517 |
| URL الوصول: | http://arxiv.org/abs/2105.09907 |
| رقم الأكسشن: | edsarx.2105.09907 |
| قاعدة البيانات: | arXiv |
| DOI: | 10.1109/TCSVT.2021.3078517 |
|---|