1

TANDEM: Tracking and Dense Mapping in Real-time using Deep Multi-view Stereo

MonoRec: Semi-Supervised Dense Reconstruction in Dynamic Environments from a Single Moving Camera

In this paper, we propose MonoRec, a semi-supervised monocular dense reconstruction architecture that predicts depth maps from a single moving camera in dynamic environments. MonoRec is based on a multi-view stereo setting which encodes the …

Tight Integration of Feature-based Relocalization in Monocular Direct Visual Odometry

In this paper we propose a framework for integrating map-based relocalization into online direct visual odometry. To achieve map-based relocalization for direct methods, we integrate image features into Direct Sparse Odometry (DSO) and rely on …

4Seasons: A Cross-Season Dataset for Multi-Weather SLAM in Autonomous Driving

On the Fusion of Camera and Lidar for 3D Object Detection and Classification

In this paper we present a sensor fusion framework for the detection and classification of objects in autonomous driving applications. The presented method uses a state-of-the-art convolutional neural network (CNN) to detect and classify object from …

Generating a Totally Focused Colour Image from Recordings of a Plenoptic Camera

This paper presents a method to calculate a totally focussed colour image from recordings of a plenoptic camera. The three colour channels have to be extracted from the raw image. The virtual depth is estimated analyzing the disparities of image …

Scale-Awareness of Light Field Camera based Visual Odometry

We propose a novel direct visual odometry algorithm formicro-lens-array-based light field cameras. The algorithm calculates adetailed, semi-dense 3D point cloud of its environment. Thisis achievedby establishing probabilistic depth hypotheses based …

Metric Calibration of a Focused Plenoptic Camera based on a 3D Calibration Target

In this paper we present a new calibration approach for focused plenoptic cameras. We derive a new mathematical projection model of afocused plenoptic camera which considers lateral as well as depth distortion. Therefore, we derive a new depth …

Investigating Mathematical Models for Focused Plenoptic Cameras

This paper presents a mathematical projection model for focused plenoptic cameras. The model defines the projection from object space to the virtual image space inside the plenoptic camera. We estimate the camera model by performing bundle adjustment …

Depth Estimation from Micro Images of a Plenoptic Camera

This paper presents a method to calculate the depth values of 3D points by means of a plenoptic camera. Opposed to other approaches which use the totally focused image to detect points, we operate directly on the micro images taking thus advantage of …