Search
Results
-
Image-to-image translation for enhanced feature matching, image retrieval and visual localization
(2019)ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information SciencesThe performance of machine learning and deep learning algorithms for image analysis depends significantly on the quantity and quality of the training data. The generation of annotated training data is often costly, time-consuming and laborious. Data augmentation is a powerful option to overcome these drawbacks. Therefore, we augment training data by rendering images with arbitrary poses from 3D models to increase the quantity of training ...Conference Paper -
Image localization in satellite imagery with feature-based indexing
(2008)International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences ~ XXIst ISPRS Congress: Technical Commission IIIThis paper presents a method to index ortho-map databases with image-based features and search a map database for regions that matchquery images of unknown scales and rotations. The proposed method uses image-based features to index the 2D map locations. Imagefeature extractors normally generate features with location, orientation, shape, and a descriptor for normalized image patch. In a mapdatabase, the geographical location, orientation ...Conference Paper -
3D Reconstruction of architectural scenes from uncalibrated video sequences
(2009)International Archives of the Photogrammetry, Remote Sensing and Spatial Information SciencesIn this paper we present a system for three-dimensional reconstruction of architectural scenes from uncalibrated videos. These videosmight be recorded using hand-held cameras, downloaded from the internet or taken from archival sources. Because we do not requireprior knowledge of the camera’s internal parameters such as focal length, center of projection, and radial distortion we can deal withvideos from uncontrolled sources. We present ...Conference Paper -
Real-Time Video-Based Reconstruction of Urban Environments
(2007)International Archives of the Photogrammetry, Remote Sensing and Spatial Information SciencesWe present an approach for automatic 3D reconstruction of outdoor scenes using computer vision techniques. Our system collectsvideo, GPS and INS data which are processed in real-time to produce geo-registered, detailed 3D models that represent the geometryand appearance of the world. These models are generated without manual measurements or markers in the scene and can be used forvisualization from arbitrary viewpoints, documentation and ...Conference Paper -
Finding the exact rotation between two images independently of the translation
(2012)Conference Paper -
Absolute scale in structure from motion from a single vehicle mounted camera by exploiting nonholonomic constraints
(2009)2009 IEEE 12th International Conference on Computer VisionConference Paper -
Real-Time 6D Stereo Visual Odometry with Non-Overlapping Fields of View
(2012)IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2012 : 16 - 21 June 2012, Providence, RI, USAConference Paper -
Semantically Informed Multiview Surface Refinement
(2017)2017 IEEE International Conference on Computer Vision (ICCV)Conference Paper -
Uncertainty Quantification in CNN-Based Surface Prediction Using Shape Priors
(2018)Lecture Notes in Computer Science ~ Shape in Medical Imaging International Workshop, ShapeMI 2018, held in conjunction with MICCAI 2018, Granada, Spain, September 20, 2018, ProceedingsSurface reconstruction is a vital tool in a wide range of areas of medical image analysis and clinical research. Despite the fact that many methods have proposed solutions to the reconstruction problem, most, due to their deterministic nature, do not directly address the issue of quantifying uncertainty associated with their predictions. We remedy this by proposing a novel probabilistic deep learning approach capable of simultaneous surface ...Conference Paper -
Learning Motion Priors for 4D Human Body Capture in 3D Scenes
(2021)2021 IEEE/CVF International Conference on Computer Vision (ICCV)Recovering high-quality 3D human motion in complex scenes from monocular videos is important for many applications, ranging from AR/VR to robotics. However, capturing realistic human-scene interactions, while dealing with occlusions and partial views, is challenging; current approaches are still far from achieving compelling results. We address this problem by proposing LEMO: LEarning human MOtion priors for 4D human body capture. By ...Conference Paper