Abstract-In this paper, we propose a dense visual SLAM method for RGB-D cameras that minimizes both the photometric and the depth error over all pixels. In contrast to sparse, feature-based methods, this allows us to better exploit the available information in the image data which leads to higher pose accuracy. Furthermore, we propose an entropy-based similarity measure for keyframe selection and loop closure detection. From all successful matches, we build up a graph that we optimize using the g2o framework. We evaluated our approach extensively on publicly available benchmark datasets, and found that it performs well in scenes with low texture as well as low structure. In direct comparison to several stateof-the-art methods, our approach yields a significantly lower trajectory error. We release our software as open-source.

Abstract-The goal of our work is to provide a fast and accurate method to estimate the camera motion from RGB-D images. Our approach registers two consecutive RGB-D frames directly upon each other by minimizing the photometric error. We estimate the camera motion using non-linear minimization in combination with a coarse-to-fine scheme. To allow for noise and outliers in the image data, we propose to use a robust error function that reduces the influence of large residuals. Furthermore, our formulation allows for the inclusion of a motion model which can be based on prior knowledge, temporal filtering, or additional sensors like an IMU. Our method is attractive for robots with limited computational resources as it runs in real-time on a single CPU core and has a small, constant memory footprint. In an extensive set of experiments carried out both on a benchmark dataset and synthetic data, we demonstrate that our approach is more accurate and robust than previous methods. We provide our software under an open source license.

Abstract-The ability to quickly acquire 3D models is an essential capability needed in many disciplines including robotics, computer vision, geodesy, and architecture. In this paper we present a novel method for real-time camera tracking and 3D reconstruction of static indoor environments using an RGB-D sensor. We show that by representing the geometry with a signed distance function (SDF), the camera pose can be efficiently estimated by directly minimizing the error of the depth images on the SDF. As the SDF contains the distances to the surface for each voxel, the pose optimization can be carried out extremely fast. By iteratively estimating the camera poses and integrating the RGB-D data in the voxel grid, a detailed reconstruction of an indoor environment can be achieved. We present reconstructions of several rooms using a hand-held sensor and from onboard an autonomous quadrocopter. Our extensive evaluation on publicly available benchmark data shows that our approach is more accurate and robust than the iterated closest point algorithm (ICP) used by KinectFusion, and yields often a comparable accuracy at much higher speed to feature-based bundle adjustment methods such as RGB-D SLAM for up to medium-sized scenes.

No abstract

Abstract-Visual scene understanding is an important capability that enables robots to purposefully act in their environment. In this paper, we propose a novel deep neural network approach to predict semantic segmentation from RGB-D sequences. The key innovation is to train our network to predict multi-view consistent semantics in a self-supervised way. At test time, its semantics predictions can be fused more consistently in semantic keyframe maps than predictions of a network trained on individual views. We base our network architecture on a recent single-view deep learning approach to RGB and depth fusion for semantic object-class segmentation and enhance it with multi-scale loss minimization. We obtain the camera trajectory using RGB-D SLAM and warp the predictions of RGB-D images into ground-truth annotated frames in order to enforce multi-view consistency during training. At test time, predictions from multiple views are fused into keyframes. We propose and analyze several methods for enforcing multi-view consistency during training and testing. We evaluate the benefit of multi-view consistency training and demonstrate that pooling of deep features and fusion over multiple views outperforms single-view baselines on the NYUDv2 benchmark for semantic segmentation. Our end-to-end trained network achieves stateof-the-art performance on the NYUDv2 dataset in single-view segmentation as well as multi-view semantic fusion.