Zobrazeno 1 - 10
of 635
pro vyhledávání: '"Kuhn, Andreas"'
Autor:
Santellani, Emanuele, Zach, Martin, Sormann, Christian, Rossi, Mattia, Kuhn, Andreas, Fraundorfer, Friedrich
The extraction of keypoints in images is at the basis of many computer vision applications, from localization to 3D reconstruction. Keypoints come with a score permitting to rank them according to their quality. While learned keypoints often exhibit
Externí odkaz:
http://arxiv.org/abs/2408.17149
Autor:
Santellani, Emanuele, Sormann, Christian, Rossi, Mattia, Kuhn, Andreas, Fraundorfer, Friedrich
In this work we introduce S-TREK, a novel local feature extractor that combines a deep keypoint detector, which is both translation and rotation equivariant by design, with a lightweight deep descriptor extractor. We train the S-TREK keypoint detecto
Externí odkaz:
http://arxiv.org/abs/2308.14598
Autor:
Sormann, Christian, Santellani, Emanuele, Rossi, Mattia, Kuhn, Andreas, Fraundorfer, Friedrich
We propose a novel approach for deep learning-based Multi-View Stereo (MVS). For each pixel in the reference image, our method leverages a deep architecture to search for the corresponding point in the source image directly along the corresponding ep
Externí odkaz:
http://arxiv.org/abs/2212.06626
Autor:
Santellani, Emanuele, Sormann, Christian, Rossi, Mattia, Kuhn, Andreas, Fraundorfer, Friedrich
Establishing a sparse set of keypoint correspon dences between images is a fundamental task in many computer vision pipelines. Often, this translates into a computationally expensive nearest neighbor search, where every keypoint descriptor at one ima
Externí odkaz:
http://arxiv.org/abs/2208.05350
We present a novel deep-learning-based method for Multi-View Stereo. Our method estimates high resolution and highly precise depth maps iteratively, by traversing the continuous space of feasible depth values at each pixel in a binary decision fashio
Externí odkaz:
http://arxiv.org/abs/2111.14420
Autor:
Kuhn, Andreas, Fischer, Sabine C.
The Vicsek model (Vicsek et al. 1995) is a very popular minimalist model to study active matter with a number of applications to biological systems at different length scales. With its off-lattice implementation and periodic boundary conditions, it a
Externí odkaz:
http://arxiv.org/abs/2105.08792
Autor:
Sormann, Christian, Knöbelreiter, Patrick, Kuhn, Andreas, Rossi, Mattia, Pock, Thomas, Fraundorfer, Friedrich
In this work, we propose BP-MVSNet, a convolutional neural network (CNN)-based Multi-View-Stereo (MVS) method that uses a differentiable Conditional Random Field (CRF) layer for regularization. To this end, we propose to extend the BP layer and add w
Externí odkaz:
http://arxiv.org/abs/2010.12436
Depth estimation is an essential component in understanding the 3D geometry of a scene, with numerous applications in urban and indoor settings. These scenes are characterized by a prevalence of human made structures, which in most of the cases, are
Externí odkaz:
http://arxiv.org/abs/1912.01306
Deep Neural Networks (DNNs) have the potential to improve the quality of image-based 3D reconstructions. However, the use of DNNs in the context of 3D reconstruction from large and high-resolution image datasets is still an open challenge, due to mem
Externí odkaz:
http://arxiv.org/abs/1912.00439