Enabling computer systems to recognize human facial expressions is a challenging research problem with many applications in behavioral science, medicine, security, and human-machine interaction. Instead of being another approach to automatic detection of prototypic facial expressions of emotion, this work attempts to analyze subtle changes in facial behavior by recognizing facial action units (...

Reconstruction of scene geometry and semantics are important problems in vision, and increasingly brought together. The state of the art in Structure from Motion and Multi View Stereo (SfM+MVS) can already create accurate, dense reconstructions of scenes. Systems such as CMPMVS [2] are freely available and produce impressive results automatically. However, when assumptions break down or there i...

We study the problem of shape reconstruction from stereo images based on a weighted area minimization process of a depth function. As a simple example we present an eecient shape reconstruction from computer generated autostereograms. A minimal surface area based correlation is applied to accurately reconstruct the surface structure embedded rst in one autostereogram image, and next in two or m...

A method to solve oversegmentation and undersegmentation in a region-based correspondence process is presented. The approach is based on performing a preprocessing step before using existing graph based methods. This preprocessing tries to assess the possible split regions in each image, with respect to the corresponding image, and form merge regions that could map better with regions in the ot...

Contemporary benchmark methods for image inpainting are based on deep generative models and specifically leverage adversarial loss for yielding realistic reconstructions. However, these models cannot be directly applied on image/video sequences because of an intrinsic drawbackthe reconstructions might be independently realistic, but, when visualized as a sequence, often lacks fidelity to the or...

We present a novel method for creating high-resolution 3D reconstructions using RGB-D cameras, such as the Microsoft Kinect. We demonstrate how such a technique can be used both for large scale mapping and high-resolution object detection. Our work consists of two core contributions. First, we present an algorithm to generate 3D reconstructions of arbitrary resolution, up to that of the limitat...

A new version of the Earth system model of intermediate complexity, CLIMBER-2, which includes the three-dimensional polythermal ice-sheet model SICOPOLIS, is used to simulate the last glacial cycle forced by variations of the Earth’s orbital parameters and atmospheric concentration of major greenhouse gases. The climate and icesheet components of the model are coupled bi-directionally through a...

In this paper we present a dense visual odometry system for RGB-D cameras performing both photometric and geometric error minimisation to estimate the camera motion between frames. Contrary to most works in the literature, we parametrise the geometric error by the inverse depth instead of the depth, which translates into a better fit of the distribution of the geometric error to the used robust...