Mohamed Souiai

Learn More
This paper presents the first method to compute dense scene flow in real-time for RGB-D cameras. It is based on a variational formulation where brightness constancy and geometric consistency are imposed. Accounting for the depth data provided by RGB-D cameras, regularization of the flow field is imposed on the 3D surface (or set of surfaces) of the observed(More)
We propose a novel joint registration and segmentation approach to estimate scene flow from RGB-D images. Instead of assuming the scene to be composed of a number of independent rigidly-moving parts, we use non-binary labels to capture non-rigid deformations at transitions between the rigid parts of the scene. Thus, the velocity of any point can be computed(More)
Creating textured 3D scans of indoor environments has experienced a large boost with the advent of cheap commodity depth sensors. However, the quality of the acquired 3D models is often impaired by color seams in the reconstruction due to varying illumination (e.g., shadows or highlights) and object surfaces whose brightness and color vary with the(More)
In this paper, we introduce the concept of proximity priors into semantic segmentation in order to discourage the presence of certain object classes (such as 'sheep' and 'wolf') 'in the vicinity' of each other. 'Vicinity' encompasses spatial distance as well as specific spatial directions simultaneously, e.g. 'plates' are found directly above 'tables', but(More)
In this paper we give a convex optimization approach for scene understanding. Since segmentation, object recognition and scene labeling strongly benefit from each other we propose to solve these tasks within a single convex optimization problem. In contrast to previous approaches we do not rely on pre-processing techniques such as object detectors or super(More)
To obtain high-quality segmentation results the integration of semantic information is indispensable. In contrast to existing segmentation methods which use a spatial regularizer, i.e. a local interaction between image points, the co-occurrence prior [15] imposes penalties on the co-existence of different labels in a segmentation. We propose a continuous(More)
We propose an optimization algorithm for mutual information-based unsupervised figure-ground separation. The algorithm jointly estimates the color distributions of the foreground and background, and separates them based on their mutual information with geometric regularity. To this end, we revisit the notion of mutual information and reformulate it in terms(More)
We present an active learning framework for image segmentation with user interaction. Our system uses a sparse Gaussian Process classifier (GPC) trained on manually labeled image pixels (user scribbles) and refined in every active learning round. As a special feature, our method uses a very efficient online update rule to compute the class predictions in(More)
Despite their enormous success in solving hard combinatorial problems, convex relaxation approaches often suffer from the fact that the computed solutions are far from binary and that subsequent heuristic binarization may substantially degrade the quality of computed solutions. In this paper, we propose a novel relaxation technique which incorporates the(More)
We propose an algorithm for automatizing the task of ”Tidying up Art” introduced by the comedian Wehrli [1]. Driven by a strong sense of order and tidyness, Wehrli systematically dissects famous artworks into their constituents and rearranges them according to certain ordering principles. The proposed algorithmic solution to this problem builds up on a(More)