EgoActive: Integrated Wireless Wearable Sensors for Capturing Infant Egocentric Auditory-Visual Statistics and Autonomic Nervous System Function 'in the Wild'.

There have been sustained efforts toward using naturalistic methods in developmental science to measure infant behaviors in the real world from an egocentric perspective because statistical regularities in the environment can shape and be shaped by the developing infant. However, there is no user-friendly and unobtrusive technology to densely and reliably sample life in the wild. To address this gap, we present the design, implementation and validation of the EgoActive platform, which addresses limitations of existing wearable technologies for developmental research. EgoActive records the active infants' egocentric perspective of the world via a miniature wireless head-mounted camera concurrently with their physiological responses to this input via a lightweight, wireless ECG/acceleration sensor. We also provide software tools to facilitate data analyses. Our validation studies showed that the cameras and body sensors performed well. Families also reported that the platform was comfortable, easy to use and operate, and did not interfere with daily activities. The synchronized multimodal data from the EgoActive platform can help tease apart complex processes that are important for child development to further our understanding of areas ranging from executive function to emotion processing and social learning.

Outdoor Inverse Rendering From a Single Image Using Multiview Self-Supervision.

In this paper we show how to perform scene-level inverse rendering to recover shape, reflectance and lighting from a single, uncontrolled image using a fully convolutional neural network. The network takes an RGB image as input, regresses albedo, shadow and normal maps from which we infer least squares optimal spherical harmonic lighting coefficients. Our network is trained using large uncontrolled multiview and timelapse image collections without ground truth. By incorporating a differentiable renderer, our network can learn from self-supervision. Since the problem is ill-posed we introduce additional supervision. Our key insight is to perform offline multiview stereo (MVS) on images containing rich illumination variation. From the MVS pose and depth maps, we can cross project between overlapping views such that Siamese training can be used to ensure consistent estimation of photometric invariants. MVS depth also provides direct coarse supervision for normal map estimation. We believe this is the first attempt to use MVS supervision for learning inverse rendering. In addition, we learn a statistical natural illumination prior. We evaluate performance on inverse rendering, normal map estimation and intrinsic image decomposition benchmarks.

Uncalibrated, Two Source Photo-Polarimetric Stereo.

In this paper we present methods for estimating shape from polarisation and shading information, i.e. photo-polarimetric shape estimation, under varying, but unknown, illumination, i.e. in an uncalibrated scenario. We propose several alternative photo-polarimetric constraints that depend upon the partial derivatives of the surface and show how to express them in a unified system of partial differential equations of which previous work is a special case. By careful combination and manipulation of the constraints, we show how to eliminate non-linearities such that a discrete version of the problem can be solved using linear least squares. We derive a minimal, combinatorial approach for two source illumination estimation which we use with RANSAC for robust light direction and intensity estimation. We also introduce a new method for estimating a polarisation image from multichannel data and provide methods for estimating albedo and refractive index. We evaluate lighting, shape, albedo and refractive index estimation methods on both synthetic and real-world data showing improvements over existing state-of-the-art.

Towards a Complete 3D Morphable Model of the Human Head.

Three-dimensional morphable models (3DMMs) are powerful statistical tools for representing the 3D shapes and textures of an object class. Here we present the most complete 3DMM of the human head to date that includes face, cranium, ears, eyes, teeth and tongue. To achieve this, we propose two methods for combining existing 3DMMs of different overlapping head parts: (i). use a regressor to complete missing parts of one model using the other, and (ii). use the Gaussian Process framework to blend covariance matrices from multiple models. Thus, we build a new combined face-and-head shape model that blends the variability and facial detail of an existing face model (the LSFM) with the full head modelling capability of an existing head model (the LYHM). Then we construct and fuse a highly-detailed ear model to extend the variation of the ear shape. Eye and eye region models are incorporated into the head model, along with basic models of the teeth, tongue and inner mouth cavity. The new model achieves state-of-the-art performance. We use our model to reconstruct full head representations from single, unconstrained images allowing us to parameterize craniofacial shape and texture, along with the ear shape, eye gaze and eye color.

Height-from-Polarisation with Unknown Lighting or Albedo.

We present a method for estimating surface height directly from a single polarisation image simply by solving a large, sparse system of linear equations. To do so, we show how to express polarisation constraints as equations that are linear in the unknown height. The local ambiguity in the surface normal azimuth angle is resolved globally when the optimal surface height is reconstructed. Our method is applicable to dielectric objects exhibiting diffuse and specular reflectance, though lighting and albedo must be known. We relax this requirement by showing that either spatially varying albedo or illumination can be estimated from the polarisation image alone using nonlinear methods. In the case of illumination, the estimate can only be made up to a binary ambiguity which we show is a generalised Bas-relief transformation corresponding to the convex/concave ambiguity. We believe that our method is the first passive, monocular shape-from-x technique that enables well-posed height estimation with only a single, uncalibrated illumination condition. We present results on real world data, including in uncontrolled, outdoor illumination.

Structure-From-Motion in Spherical Video Using the von Mises-Fisher Distribution.

In this paper, we present a complete pipeline for computing structure-from-motion from the sequences of spherical images. We revisit problems from multiview geometry in the context of spherical images. In particular, we propose methods suited to spherical camera geometry for the spherical-n-point problem (estimating camera pose for a spherical image) and calibrated spherical reconstruction (estimating the position of a 3-D point from multiple spherical images). We introduce a new probabilistic interpretation of spherical structure-from-motion which uses the von Mises-Fisher distribution to model noise in spherical feature point positions. This model provides an alternate objective function that we use in bundle adjustment. We evaluate our methods quantitatively and qualitatively on both synthetic and real world data and show that our methods developed for spherical images outperform straightforward adaptations of methods developed for perspective images. As an application of our method, we use the structure-from-motion output to stabilise the viewing direction in fully spherical video.

Modelling the perceptual similarity of facial expressions from image statistics and neural responses.

The ability to perceive facial expressions of emotion is essential for effective social communication. We investigated how the perception of facial expression emerges from the image properties that convey this important social signal, and how neural responses in face-selective brain regions might track these properties. To do this, we measured the perceptual similarity between expressions of basic emotions, and investigated how this is reflected in image measures and in the neural response of different face-selective regions. We show that the perceptual similarity of different facial expressions (fear, anger, disgust, sadness, happiness) can be predicted by both surface and feature shape information in the image. Using block design fMRI, we found that the perceptual similarity of expressions could also be predicted from the patterns of neural response in the face-selective posterior superior temporal sulcus (STS), but not in the fusiform face area (FFA). These results show that the perception of facial expression is dependent on the shape and surface properties of the image and on the activity of specific face-selective regions.

Inverse rendering of faces with a 3D morphable model.

In this paper, we present a complete framework to inverse render faces with a 3D Morphable Model (3DMM). By decomposing the image formation process into geometric and photometric parts, we are able to state the problem as a multilinear system which can be solved accurately and efficiently. As we treat each contribution as independent, the objective function is convex in the parameters and a global solution is guaranteed. We start by recovering 3D shape using a novel algorithm which incorporates generalization error of the model obtained from empirical measurements. We then describe two methods to recover facial texture, diffuse lighting, specular reflectance, and camera properties from a single image. The methods make increasingly weak assumptions and can be solved in a linear fashion. We evaluate our findings on a publicly available database, where we are able to outperform an existing state-of-the-art algorithm. We demonstrate the usability of the recovered parameters in a recognition experiment conducted on the CMU-PIE database.

Automated construction of low-resolution, texture-mapped, class-optimal meshes.

In this paper, we present a framework for the groupwise processing of a set of meshes in dense correspondence. Such sets arise when modeling 3D shape variation or tracking surface motion over time. We extend a number of mesh processing tools to operate in a groupwise manner. Specifically, we present a geodesic-based surface flattening and spectral clustering algorithm which estimates a single class-optimal flattening. We also show how to modify an iterative edge collapse algorithm to perform groupwise simplification while retaining the correspondence of the data. Finally, we show how to compute class-optimal texture coordinates for the simplified meshes. We present alternative algorithms for topologically symmetric data which yield a symmetric flattening and low-resolution mesh topology. We present flattening, simplification, and texture mapping results on three different data sets and show that our approach allows the construction of low-resolution 3D morphable models.

The M170 reflects a viewpoint-dependent representation for both familiar and unfamiliar faces.

The aim of this study was to determine the extent to which the neural representation of faces in visual cortex is viewpoint dependent or viewpoint invariant. Magnetoencephalography was used to measure evoked responses to faces during an adaptation paradigm. Using familiar and unfamiliar faces, we compared the amplitude of the M170 response to repeated images of the same face with images of different faces. We found a reduction in the M170 amplitude to repeated presentations of the same face image compared with images of different faces when shown from the same viewpoint. To establish if this adaptation to the identity of a face was invariant to changes in viewpoint, we varied the viewing angle of the face within a block. We found a reduction in response was no longer evident when images of the same face were shown from different viewpoints. This viewpoint-dependent pattern of results was the same for both familiar and unfamiliar faces. These results imply that either the face-selective M170 response reflects an early stage of face processing or that the computations underlying face recognition depend on a viewpoint-dependent neuronal representation.

A coupled statistical model for face shape recovery from brightness images.

We focus on the problem of developing a coupled statistical model that can be used to recover facial shape from brightness images of faces. We study three alternative representations for facial shape. These are the surface height function, the surface gradient, and a Fourier basis representation. We jointly capture variations in intensity and the surface shape representations using a coupled statistical model. The model is constructed by performing principal components analysis on sets of parameters describing the contents of the intensity images and the facial shape representations. By fitting the coupled model to intensity data, facial shape is implicitly recovered from the shape parameters. Experiments show that the coupled model is able to generate accurate shape from out-of-training-sample intensity images.

Recovering facial shape using a statistical model of surface normal direction.

In this paper, we show how a statistical model of facial shape can be embedded within a shape-from-shading algorithm. We describe how facial shape can be captured using a statistical model of variations in surface normal direction. To construct this model, we make use of the azimuthal equidistant projection to map the distribution of surface normals from the polar representation on a unit sphere to Cartesian points on a local tangent plane. The distribution of surface normal directions is captured using the covariance matrix for the projected point positions. The eigenvectors of the covariance matrix define the modes of shape-variation in the fields of transformed surface normals. We show how this model can be trained using surface normal data acquired from range images and how to fit the model to intensity images of faces using constraints on the surface normal direction provided by Lambert's law. We demonstrate that the combination of a global statistical constraint and local irradiance constraint yields an efficient and accurate approach to facial shape recovery and is capable of recovering fine local surface details. We assess the accuracy of the technique on a variety of images with ground truth and real-world images.