Zobrazeno 1 - 10
of 16
pro vyhledávání: '"Bökman, Georg"'
We propose a way to train deep learning based keypoint descriptors that makes them approximately equivariant for locally affine transformations of the image plane. The main idea is to use the representation theory of GL(2) to generalize the recently
Externí odkaz:
http://arxiv.org/abs/2408.14186
Autor:
Gao, Jialin, Ong, Bill, Lwi, Darld, Ng, Zhen Hao, Yee, Xun Wei, Mak, Mun-Thye, Ng, Wee Siong, Ng, See-Kiong, Teo, Hui Ying, Khoo, Victor, Bökman, Georg, Edstedt, Johan, Brodt, Kirill, Boittiaux, Clémentin, Ferrera, Maxime, Konev, Stepan
Publikováno v:
Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence Demo Track (2024) 8661-8664
Research in 3D mapping is crucial for smart city applications, yet the cost of acquiring 3D data often hinders progress. Visual localization, particularly monocular camera position estimation, offers a solution by determining the camera's pose solely
Externí odkaz:
http://arxiv.org/abs/2407.18590
In this paper, we analyze and improve into the recently proposed DeDoDe keypoint detector. We focus our analysis on some key issues. First, we find that DeDoDe keypoints tend to cluster together, which we fix by performing non-max suppression on the
Externí odkaz:
http://arxiv.org/abs/2404.08928
Image keypoint descriptions that are discriminative and matchable over large changes in viewpoint are vital for 3D reconstruction. However, descriptions output by learned descriptors are typically not robust to camera rotation. While they can be made
Externí odkaz:
http://arxiv.org/abs/2312.02152
Autor:
Bökman, Georg, Edstedt, Johan
We present the top ranked solution for the AISG-SLA Visual Localisation Challenge benchmark (IJCAI 2023), where the task is to estimate relative motion between images taken in sequence by a camera mounted on a car driving through an urban scene. For
Externí odkaz:
http://arxiv.org/abs/2310.01092
Keypoint detection is a pivotal step in 3D reconstruction, whereby sets of (up to) K points are detected in each view of a scene. Crucially, the detected points need to be consistent between views, i.e., correspond to the same 3D point in the scene.
Externí odkaz:
http://arxiv.org/abs/2308.08479
Autor:
Bökman, Georg, Kahl, Fredrik
Many data symmetries can be described in terms of group equivariance and the most common way of encoding group equivariances in neural networks is by building linear layers that are group equivariant. In this work we investigate whether equivariance
Externí odkaz:
http://arxiv.org/abs/2305.17017
Feature matching is an important computer vision task that involves estimating correspondences between two images of a 3D scene, and dense methods estimate all such correspondences. The aim is to learn a robust model, i.e., a model able to match unde
Externí odkaz:
http://arxiv.org/abs/2305.15404
Equivariance of linear neural network layers is well studied. In this work, we relax the equivariance condition to only be true in a projective sense. We propose a way to construct a projectively equivariant neural network through building a standard
Externí odkaz:
http://arxiv.org/abs/2209.14719
Autor:
Bökman, Georg, Kahl, Fredrik
The aim of this paper is to demonstrate that a state of the art feature matcher (LoFTR) can be made more robust to rotations by simply replacing the backbone CNN with a steerable CNN which is equivariant to translations and image rotations. It is exp
Externí odkaz:
http://arxiv.org/abs/2204.10144