Gernot Riegler

Learn More
In 3 experiments, the implicit memory tests of word fragment and word stem completion showed comparable effects over several variables: Study of words produced more priming than did study of pictures, no levels-of-processing effect occurred for words, more priming was obtained from pictures when Ss imaged the pictures' names than when they rated them for(More)
The effects of generation on the long-term retention of item and order information were examined in a between-list design in 3 experiments. In each experiment, completing word fragments during presentation significantly impaired long-term retention of serial order, as measured by either a reconstruction task or the amount of input-output correspondence in(More)
We present OctNet, a representation for deep learning with sparse 3D data. In contrast to existing models, our representation enables 3D convolutional networks which are both deep and high resolution. Towards this goal, we exploit the sparsity in the input data to hierarchically partition the space using a set of unbalanced octrees where each leaf node(More)
We present Hough Networks (HNs), a novel method that combines the idea of Hough Forests (HFs) [12] with Convolutional Neural Networks (CNNs) [18]. Similar to HFs we perform a simultaneous classification and regression on densely extracted image patches. But instead of a Random Forest (RF) we utilize a CNN which is able to learn higherorder feature(More)
While many recent hand pose estimation methods critically rely on a training set of labelled frames, the creation of such a dataset is a challenging task that has been overlooked so far. As a result, existing datasets are limited to a few sequences and individuals, with limited accuracy, and this prevents these methods from delivering their full potential.(More)
We present a novel method for dense variational scene flow estimation based a multiscale Ternary Census Transform in combination with a patchwise Closest Points depth data term. On the one hand, the Ternary Census Transform in the intensity data term is capable of handling illumination changes, low texture and noise. On the other hand, the patchwise Closest(More)
Single image super-resolution is an important task in the field of computer vision and finds many practical applications. Current state-of-the-art methods typically rely on machine learning algorithms to infer a mapping from low-to high-resolution images. These methods use a single fixed blur kernel during training and, consequently, assume the exact same(More)
In this paper, we present a learning based approach to depth fusion, i.e., dense 3D reconstruction from multiple depth images. The most common approach to depth fusion is based on averaging truncated signed distance functions, which was originally proposed by Curless and Levoy in 1996. While this method is simple and provides great results, it is not able(More)
In this paper we present a novel method to accurately estimate the dense 3D motion field, known as scene flow, from depth and intensity acquisitions. The method is formulated as a convex energy optimization, where the motion warping of each scene point is estimated through a projection and back-projection directly in 3D space. We utilize higher order(More)