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 1 norm in the data fidelity term. This formulation can preserve discontinuities in the flow field and offers an increased robust-ness(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)
Fig. 1. Optical flow for the backyard and mini cooper scene of the Middlebury optical flow benchmark. Optical flow captures the dynamics of a scene by estimating the motion of every pixel between two frames of an image sequence. The displacement of every pixel is shown as displacement vectors on top of the commonly used flow color scheme (see Figure 5).(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 clean-up step of a real-time dense stereo method based on plane sweeping with multiple sweeping(More)
This article presents an approach for mod-eling 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(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)
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)
We describe a " log-bilinear " model that computes class probabilities by combining an input vector multiplicatively with a vector of binary latent variables. Even though the latent variables can take on exponentially many possible combinations of values, we can efficiently compute the exact probability of each class by marginalizing over the latent(More)