Christopher Zach

Learn More
Variational methods are among the most successful approaches to calculate the optical flow between two image frames. A particularly appealing formulation is based on total variation (TV) regularization and the robust L norm in the data fidelity term. This formulation can preserve discontinuities in the flow field and offers an increased robustness against(More)
Efficient view registration with respect to a given 3D reconstruction has many applications like inside-out tracking in indoor and outdoor environments, and geo-locating images from large photo collections. We present a fast location recognition technique based on structure from motion point clouds. Vocabulary tree-based indexing of features directly(More)
A look at the Middlebury optical flow benchmark [5] reveals that nowadays variational methods yield the most accurate optical flow fields between two image frames. In this work we propose an improvement variant of the original duality based TV-L optical flow algorithm in [31] and provide implementation details. This formulation can preserve discontinuities(More)
This article presents an approach for modeling landmarks based on large-scale, heavily contaminated image collections gathered from the Internet. Our system efficiently combines 2D appearance and 3D geometric constraints to extract scene summaries and construct 3D models. In the first stage of processing, images are clustered based on low-dimensional global(More)
This work presents a real-time, data-parallel approach for global label assignment on regular grids. The labels are selected according to a Markov random field energy with a Potts prior term for binary interactions. We apply the proposed method to accelerate the cleanup step of a real-time dense stereo method based on plane sweeping with multiple sweeping(More)
We address the problem of inferring the pose of an RGB-D camera relative to a known 3D scene, given only a single acquired image. Our approach employs a regression forest that is capable of inferring an estimate of each pixel's correspondence to 3D points in the scene's world coordinate frame. The forest uses only simple depth and RGB pixel comparison(More)
Robust integration of range images is an important task for building high-quality 3D models. Since range images, and in particular range maps from stereo vision, may have a substantial amount of outliers, any integration approach aiming at high-quality models needs an increased level of robustness. Additionally, a certain level of regularization is required(More)
Repetitive and ambiguous visual structures in general pose a severe problem in many computer vision applications. Identification of incorrect geometric relations between images solely based on low level features is not always possible, and a more global reasoning approach about the consistency of the estimated relations is required. We propose to utilize(More)
High-performance feature tracking from video input is a valuable tool in many computer vision techniques and mixed reality applications. This work presents a refined and substantially accelerated approach to KLT feature tracking performed on the GPU. Additionally, a global gain ratio between successive frames is estimated to compensate for changes in the(More)
Reconstructing the 3D surface from a set of provided range images – acquired by active or passive sensors – is an important step to generate faithful virtual models of real objects or environments. Since several approaches for high quality fusion of range images are already known, the runtime efficiency of the respective methods are of increased interest.(More)