activity
20182021
most citedSelf-Supervised Learning for Monocular Depth Estimation from Aerial Imagery

10 citations · 25 across the 4 of their papers we have counts for

collaborators

7 papers

cs.CV2021

Real-time dense 3D Reconstruction from monocular video data captured by low-cost UAVs

Max Hermann, Boitumelo Ruf, Martin Weinmann

Real-time 3D reconstruction enables fast dense mapping of the environment which benefits numerous applications, such as navigation or live evaluation of an emergency. In contrast t…

cs.CV202110 cited

FAIR1M: A Benchmark Dataset for Fine-grained Object Recognition in High-Resolution Remote Sensing Imagery

Xian Sun, Peijin Wang, Zhiyuan Yan +11

With the rapid development of deep learning, many deep learning-based approaches have made great achievements in object detection task. It is generally known that deep learning is…

cs.CV202010 cited

Self-Supervised Learning for Monocular Depth Estimation from Aerial Imagery

Max Hermann, Boitumelo Ruf, Martin Weinmann +1

Supervised learning based methods for monocular depth estimation usually require large amounts of extensively annotated training data. In the case of aerial imagery, this ground tr…

cs.CV20205 cited

Voxel-Based Indoor Reconstruction From HoloLens Triangle Meshes

P. Hübner, M. Weinmann, S. Wursthorn

Current mobile augmented reality devices are often equipped with range sensors. The Microsoft HoloLens for instance is equipped with a Time-Of-Flight (ToF) range camera providing c…

cs.CV2019

Efficient Surface-Aware Semi-Global Matching with Multi-View Plane-Sweep Sampling

Boitumelo Ruf, Thomas Pollok, Martin Weinmann

Online augmentation of an oblique aerial image sequence with structural information is an essential aspect in the process of 3D scene interpretation and analysis. One key aspect in…

cs.CV2019

Automatic Co-Registration of Aerial Imagery and Untextured Model Data Utilizing Average Shading Gradients

Sylvia Schmitz, Martin Weinmann, Boitumelo Ruf

The comparison of current image data with existing 3D model data of a scene provides an efficient method to keep models up to date. In order to transfer information between 2D and…