3D Face Alignment in the Wild: A Landmark-Free, Nose-Based Approach
We present a methodology for 3D face alignment in the wild, such that only the nose is required as input for assessing the position of the landmarks. Our approach works by first detecting the nose region, which is used for estimating the head pose. After
- PDF / 3,605,488 Bytes
- 9 Pages / 439.37 x 666.142 pts Page_size
- 23 Downloads / 256 Views
stract. We present a methodology for 3D face alignment in the wild, such that only the nose is required as input for assessing the position of the landmarks. Our approach works by first detecting the nose region, which is used for estimating the head pose. After that, a generic face landmark model, obtained by averaging all training images, is rotated, translated and scaled based on the size and localization of the nose. Because little information is needed and there are no refinement steps, our method is able to find suitable landmarks even in challenging poses. While not taking into account facial expressions and specific facial traits, our algorithm achieved competitive scores on the 3D Face Alignment in the Wild (3DFAW) challenge. The obtained results have the potential to be used as rough estimation of the position of the 3D face landmarks in the wild images, which can be further refined by specially designed algorithms.
Keywords: 3D face alignment wild
1
·
Head pose estimation
·
Faces in the
Introduction
Face alignment is defined as determining the position of a set of known facial points across different subjects, illuminations, expressions and poses [4]. 3D face alignment in the wild is defined as determining the position of these landmarks in the 3D space given only a 2D image acquired in unconstrained environments. This information can be used for several computer vision applications, such as face recognition [11], pose estimation [7], face tracking [14,15], 3D face reconstruction [1] and expression transfer [12,13]. Recent face alignment work can be subdivided into 2D and 3D methods. Zhu and Ramanan [19] use mixtures of trees with a shared pool of parts for sparsely aligning faces even in profile head poses, successfully calculating the position of the 2D landmarks. Ren et al. [8] uses regression local binary features to perform 2D sparse face landmark estimation at 3000 frames per second. Jeni et al. [4] is able achieve state-of-the-art real-time 3D dense face alignment by fitting a 3D model on images acquired in controlled environments. The use of cascaded c Springer International Publishing Switzerland 2016 G. Hua and H. J´ egou (Eds.): ECCV 2016 Workshops, Part II, LNCS 9914, pp. 581–589, 2016. DOI: 10.1007/978-3-319-48881-3 40
582
F.H. de Bittencourt Zavan et al.
coupled-regressors, by integrating a 3D point distribution model was proposed by Jourabloo and Liu [5] for estimating sparse 3D face landmarks in extreme poses. In this paper, we present our entry for the 3D Facial Alignment in the Wild (3DFAW) challenge. Our approach is landmark-free in the sense that it does not need any specific face information, only a detected nose region that is used to estimate the head pose. A generic face landmark model is rotated based on the head pose, translated and scaled to fit the detected nose. We choose to use the nose as basis of our work as it has been shown efficient for head pose estimation, does not deform easily when facial expressions are present, is not easily occluded by accessories and is visible ev
Data Loading...
