arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1709.01993cs.CV
收藏

用于人脸图像逆光照的标签去噪对抗网络(LDAN)

Label Denoising Adversarial Network (LDAN) for Inverse Lighting of Face Images

University of Maryland(马里兰大学)

Hao Zhou, Jin Sun, Yaser Yacoob, David W. Jacobs

摘要:

人脸图像的光照估计是一个重要的研究课题,在图像编辑、图像分解、图像伪造检测等领域有着广泛的应用。我们建议训练深度卷积神经网络(CNN)来从单个人脸图像回归照明参数。缺乏大量的地面实况照明标签的人脸图像在野外,我们使用现有的方法来估计照明参数,这被视为地面实况与未知的噪声。为了减轻这种噪声的影响,我们利用生成对抗网络(GAN)的思想,提出了一种标签去噪对抗网络(LDAN),利用具有准确地面真实的合成数据来帮助训练深度CNN,用于真实人脸图像的光照回归。实验表明,我们的网络优于现有的方法,在类似的光照条件下,产生一致的光照参数的不同的脸。此外,我们的方法在执行时间上比先前基于优化的照明估计方法快100,000倍。

英文摘要:

Lighting estimation from face images is an important task and has applications in many areas such as image editing, intrinsic image decomposition, and image forgery detection. We propose to train a deep Convolutional Neural Network (CNN) to regress lighting parameters from a single face image. Lacking massive ground truth lighting labels for face images in the wild, we use an existing method to estimate lighting parameters, which are treated as ground truth with unknown noises. To alleviate the effect of such noises, we utilize the idea of Generative Adversarial Networks (GAN) and propose a Label Denoising Adversarial Network (LDAN) to make use of synthetic data with accurate ground truth to help train a deep CNN for lighting regression on real face images. Experiments show that our network outperforms existing methods in producing consistent lighting parameters of different faces under similar lighting conditions. Moreover, our method is 100,000 times faster in execution time than prior optimization-based lighting estimation approaches.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑