Pose-preserving Cross-spectral Face Hallucination | |
Yu, Junchi1,2; Cao, Jie1,2; Li, Yi1,2; Jia, Xiaofei3; He, Ran1,2 | |
2019 | |
会议名称 | International Joint Conference on Artificial Intelligence |
会议日期 | 2019年8月10日 - 2019年8月16日 |
会议地点 | 中国澳门 |
摘要 | To narrow the inherent sensing gap in heterogeneous face recognition (HFR), recent methods have resorted to generative models and explored the “recognition via generation” framework. Even though, it remains a very challenging task to synthesize photo-realistic visible faces (VIS) from near-infrared (NIR) images especially when paired training data are unavailable. We present an approach to avert the data misalignment problem and faithfully preserve pose, expression and identity information during cross-spectral face hallucination. At the pixel level, we introduce an unsupervised attention mechanism to warping that is jointly learned with the generator to derive pixel-wise correspondence from unaligned data. At the image level, an auxiliary generator is employed to facilitate the learning of mapping from NIR to VIS domain. At the domain level, we first apply the mutual information constraint to explicitly measure the correlation between domains and thus benefit synthesis. Extensive experiments on three heterogeneous face datasets demonstrate that our approach not only outperforms current state-of-the-art HFR methods but also produce visually appealing results at a high resolution (256×256). |
收录类别 | EI |
语种 | 英语 |
七大方向——子方向分类 | 图像视频处理与分析 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/44735 |
专题 | 智能感知与计算研究中心 |
通讯作者 | He, Ran |
作者单位 | 1.中国科学院自动化研究所 2.中国科学院大学 3.华为多媒体技术中心 |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Yu, Junchi,Cao, Jie,Li, Yi,et al. Pose-preserving Cross-spectral Face Hallucination[C],2019. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Yu 等。 - 2019 - Pose-(866KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论