A 3D Morphable Eye Region Model for Gaze Estimation
Morphable face models are a powerful tool, but have previously failed to model the eye accurately due to complexities in its material and motion. We present a new multi-part model of the eye that includes a morphable model of the facial eye region, as wel
- PDF / 3,850,854 Bytes
- 17 Pages / 439.37 x 666.142 pts Page_size
- 81 Downloads / 177 Views
3
University of Cambridge, Cambridge, UK {eww23,pr10}@cl.cam.ac.uk 2 Carnegie Mellon University, Pittsburgh, USA {tbaltrus,morency}@cs.cmu.edu Max Planck Institute for Informatics, Saarbr¨ ucken, Germany [email protected]
Abstract. Morphable face models are a powerful tool, but have previously failed to model the eye accurately due to complexities in its material and motion. We present a new multi-part model of the eye that includes a morphable model of the facial eye region, as well as an anatomy-based eyeball model. It is the first morphable model that accurately captures eye region shape, since it was built from high-quality head scans. It is also the first to allow independent eyeball movement, since we treat it as a separate part. To showcase our model we present a new method for illumination- and head-pose–invariant gaze estimation from a single RGB image. We fit our model to an image through analysis-bysynthesis, solving for eye region shape, texture, eyeball pose, and illumination simultaneously. The fitted eyeball pose parameters are then used to estimate gaze direction. Through evaluation on two standard datasets we show that our method generalizes to both webcam and high-quality camera images, and outperforms a state-of-the-art CNN method achieving a gaze estimation accuracy of 9.44◦ in a challenging user-independent scenario. Keywords: Morphable model · Gaze estimation · Analysis-by-synthesis
1
Introduction
The eyes and their movements convey our attention, indicate our interests, and play a key role in communicating social and emotional information [1]. Estimating eye gaze is therefore an important problem for computer vision, with applications ranging from facial analysis [2] to gaze-based interfaces [3,4]. However, estimating gaze remotely under unconstrained lighting conditions and significant head-pose is a yet-outstanding challenge. Appearance-based methods Electronic supplementary material The online version of this chapter (doi:10. 1007/978-3-319-46448-0 18) contains supplementary material, which is available to authorized users. c Springer International Publishing AG 2016 B. Leibe et al. (Eds.): ECCV 2016, Part I, LNCS 9905, pp. 297–313, 2016. DOI: 10.1007/978-3-319-46448-0 18
298
E. Wood et al.
3D head scans Input image
Initialization
Estimated gaze
3D morphable model
Eye region 3DMM
Analysis-by-synthesis for gaze estimation
Fig. 1. Our generic gaze estimator is enabled by two contributions. First, a novel 3DMM of the eye built from high quality head scans. Second, a new method for gaze estimation – we fit our 3DMM to an image using analysis-by-synthesis, and estimate gaze from fitted parameters.
that directly estimate gaze from an eye image have recently improved upon person- and device-independent gaze estimation by learning invariances from large amounts of labelled training data. In particular, Zhang et al. trained a multi-modal convolutional neural network with 200,000 images collected during everyday laptop use [5], and Wood et al. rendered over one millio
Data Loading...
