arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1607.00659cs.CV
收藏

鲁棒的深层外观模型

Robust Deep Appearance Models

Concordia University(康考迪亚大学);Carnegie Mellon University(卡内基梅隆大学)

Kha Gia Quach, Chi Nhan Duong, Khoa Luu, Tien D. Bui

摘要:

本文提出了一种新的鲁棒深度外观模型来学习人脸图像的形状和纹理之间的非线性相关性。在该方法中,人脸图像的两个关键组成部分,即形状和纹理,分别由深度玻尔兹曼机和鲁棒深度玻尔兹曼机(RDBM)表示。RDBM是Robust Boltzmann Machines的一种替代形式,可以分离纹理建模中的损坏/遮挡像素,以获得更好的重建结果。这两个模型在顶层由受限玻尔兹曼机连接,以共同学习和捕捉面部形状和外观的变化。本文还介绍了新的拟合算法与遮挡意识,通过从RDBM重建获得的掩模。通过使用具有挑战性的人脸数据集,即野生标记人脸部分(LFPW),海伦,EURECOM和AR数据库,在各种应用中评估所提出的方法,以证明其鲁棒性和能力。

英文摘要:

This paper presents a novel Robust Deep Appearance Models to learn the non-linear correlation between shape and texture of face images. In this approach, two crucial components of face images, i.e. shape and texture, are represented by Deep Boltzmann Machines and Robust Deep Boltzmann Machines (RDBM), respectively. The RDBM, an alternative form of Robust Boltzmann Machines, can separate corrupted/occluded pixels in the texture modeling to achieve better reconstruction results. The two models are connected by Restricted Boltzmann Machines at the top layer to jointly learn and capture the variations of both facial shapes and appearances. This paper also introduces new fitting algorithms with occlusion awareness through the mask obtained from the RDBM reconstruction. The proposed approach is evaluated in various applications by using challenging face datasets, i.e. Labeled Face Parts in the Wild (LFPW), Helen, EURECOM and AR databases, to demonstrate its robustness and capabilities.

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。

↑