Zobrazeno 1 - 10
of 1 012
pro vyhledávání: '"OLSSON, CARL A."'
In this paper we tackle the problem of learning Structure-from-Motion (SfM) through the use of graph attention networks. SfM is a classic computer vision problem that is solved though iterative minimization of reprojection errors, referred to as Bund
Externí odkaz:
http://arxiv.org/abs/2308.15984
Rank and cardinality penalties are hard to handle in optimization frameworks due to non-convexity and discontinuity. Strong approximations have been a subject of intense study and numerous formulations have been proposed. Most of these can be describ
Externí odkaz:
http://arxiv.org/abs/2107.04349
Why is it that semidefinite relaxations have been so successful in numerous applications in computer vision and robotics for solving non-convex optimization problems involving rotations? In studying the empirical performance we note that there are fe
Externí odkaz:
http://arxiv.org/abs/2101.02099
Autor:
Caramaschi, Sara1 (AUTHOR) carl.magnus.olsson@mau.se, Olsson, Carl Magnus1 (AUTHOR) dario.salvi@mau.se, Orchard, Elizabeth2 (AUTHOR) elizabeth.orchard@ouh.nhs.uk, Molloy, Jackson2 (AUTHOR) jackson.molloy@ouh.nhs.uk, Salvi, Dario1 (AUTHOR)
Publikováno v:
Sensors (14248220). Apr2024, Vol. 24 Issue 8, p2632. 24p.
Monocular depth estimation is a highly challenging problem that is often addressed with deep neural networks. While these are able to use recognition of image features to predict reasonably looking depth maps the result often has low metric accuracy.
Externí odkaz:
http://arxiv.org/abs/2012.11301
Fitting a matrix of a given rank to data in a least squares sense can be done very effectively using 2nd order methods such as Levenberg-Marquardt by explicitly optimizing over a bilinear parameterization of the matrix. In contrast, when applying mor
Externí odkaz:
http://arxiv.org/abs/2003.10281
Publikováno v:
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 8474-8483
In this paper we study the convex envelopes of a new class of functions. Using this approach, we are able to unify two important classes of regularizers from unbiased non-convex formulations and weighted nuclear norm penalties. This opens up for poss
Externí odkaz:
http://arxiv.org/abs/2001.08415
Low rank recovery problems have been a subject of intense study in recent years. While the rank function is useful for regularization it is difficult to optimize due to its non-convexity and discontinuity. The standard remedy for this is to exchange
Externí odkaz:
http://arxiv.org/abs/1909.13363
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Sparsity and rank functions are important ways of regularizing under-determined linear systems. Optimization of the resulting formulations is made difficult since both these penalties are non-convex and discontinuous. The most common remedy is to ins
Externí odkaz:
http://arxiv.org/abs/1812.11329