SLAM is an abbreviation for simultaneous localization and map**, which is a technique for
estimating sensor motion and reconstructing structure in an unknown environment …

Efficiently reconstructing complex and intricate surfaces at scale is a long-standing goal in
machine perception. To address this problem we introduce Deep Local Shapes (DeepLS), a …

The assumption of scene rigidity is typical in SLAM algorithms. Such a strong assumption
limits the use of most visual SLAM systems in populated real-world environments, which are …

Direct Sparse Odometry (DSO) is a visual odometry method based on a novel, highly
accurate sparse and direct structure and motion formulation. It combines a fully direct …

Maps are a key component in image-based camera localization and visual SLAM systems:
they are used to establish geometric constraints between images, correct drift in relative …

We propose a direct (feature-less) monocular SLAM algorithm which, in contrast to current
state-of-the-art regarding direct methods, allows to build large-scale, consistent maps of the …

Abstract We propose Stereo Direct Sparse Odometry (Stereo DSO) as a novel method for
highly accurate real-time visual odometry estimation of large-scale environments from stereo …

We introduce the Imperial College London and National University of Ireland Maynooth (ICL-
NUIM) dataset for the evaluation of visual odometry, 3D reconstruction and SLAM algorithms …

In this paper, we present a novel benchmark for the evaluation of RGB-D SLAM systems. We
recorded a large set of image sequences from a Microsoft Kinect with highly accurate and …

We present a system for accurate real-time map** of complex and arbitrary indoor scenes
in variable lighting conditions, using only a moving low-cost depth camera and commodity …