no code implementations • CVPR 2024 • Yaroslava Lochman, Carl Olsson, Christopher Zach
Clustering multiple motions from observed point trajectories is a fundamental task in understanding dynamic scenes.
1 code implementation • CVPR 2024 • Lucas Brynte, José Pedro Iglesias, Carl Olsson, Fredrik Kahl
In this paper we tackle the problem of learning Structure-from-Motion (SfM) through the use of graph attention networks.
1 code implementation • CVPR 2023 • Yaqing Ding, Jian Yang, Viktor Larsson, Carl Olsson, Kalle Åström
One of the classical multi-view geometry problems is the so called P3P problem, where the absolute pose of a calibrated camera is determined from three 2D-to-3D correspondences.
no code implementations • CVPR 2023 • José Pedro Iglesias, Amanda Nilsson, Carl Olsson
The recently introduced factorization-based pOSE methods formulate a surrogate for the bundle adjustment error without reliance on good initialization.
no code implementations • CVPR 2021 • Marcus Valtonen Ornhag, Jose Pedro Iglesias, Carl Olsson
Low rank inducing penalties have been proven to successfully uncover fundamental structures considered in computer vision and machine learning; however, such methods generally lead to non-convex optimization problems.
no code implementations • CVPR 2021 • Carl Olsson, Viktor Larsson, Fredrik Kahl
In this paper we study structure from motion problems for 1D radial cameras.
no code implementations • 6 Jan 2021 • Lucas Brynte, Viktor Larsson, José Pedro Iglesias, Carl Olsson, Fredrik Kahl
In studying the empirical performance we note that there are few failure cases reported in the literature, in particular for estimation problems with a single rotation, motivating us to gain further theoretical understanding.
no code implementations • ICCV 2021 • Jose Pedro Iglesias, Carl Olsson
Factorization methods are frequently used for structure from motion problems (SfM).
1 code implementation • 21 Dec 2020 • Patrik Persson, Linn Öström, Carl Olsson
For this purpose we propose a network structure that given an image provides a parameterization of a set of depth maps with feasible shapes.
no code implementations • ECCV 2020 • José Pedro Iglesias, Carl Olsson, Marcus Valtonen Örnhag
In contrast, when applying more general singular value penalties, such as weighted nuclear norm priors, direct optimization over the elements of the matrix is typically used.
1 code implementation • 23 Jan 2020 • Marcus Valtonen Örnhag, Carl Olsson, Anders Heyden
Lastly, we show on real non-rigid structure-from-motion (NRSfM) datasets, the issues that arise from using weighted nuclear norm penalties, and how this can be remedied using our proposed method.
Optimization and Control
no code implementations • 27 Nov 2018 • Marcus Valtonen Örnhag, Carl Olsson, Anders Heyden
Either the set of matrices with a given rank can be explicitly parametrized using a bilinear factorization, or low rank can be implicitly enforced using regularization terms penalizing non-zero singular values.
no code implementations • CVPR 2017 • Viktor Larsson, Carl Olsson
This imposes constraints on the matrix elements which allow for estimation of missing entries.
no code implementations • CVPR 2018 • Anders Eriksson, Carl Olsson, Fredrik Kahl, Tat-Jun Chin
In this paper we explore the role of duality principles within the problem of rotation averaging, a fundamental task in a wide range of computer vision applications.
no code implementations • CVPR 2016 • Erik Bylow, Carl Olsson, Fredrik Kahl, Mikael Nilsson
In the latter case, matrices are divided into sub-matrices and the envelope is computed for each sub-block individually.
no code implementations • CVPR 2016 • Johan Fredriksson, Viktor Larsson, Carl Olsson, Fredrik Kahl
Previous work on estimating the epipolar geometry of two views relies on being able to reliably match feature points based on appearance.
no code implementations • CVPR 2015 • Johan Fredriksson, Viktor Larsson, Carl Olsson
Outliers pose a problem in all real structure from motion systems.
no code implementations • ICCV 2015 • Yuri Boykov, Hossam Isack, Carl Olsson, Ismail Ben Ayed
Many standard optimization methods for segmentation and reconstruction compute ML model estimates for appearance or geometry of segments, e. g. Zhu-Yuille 1996, Torr 1998, Chan-Vese 2001, GrabCut 2004, Delong et al. 2012.
no code implementations • CVPR 2013 • Carl Olsson, Johannes Ulen, Yuri Boykov
Our theoretical and experimental results demonstrate advantages over state-of-the-art methods for 2nd order smoothness stereo.
no code implementations • 7 Mar 2013 • Carl Olsson, Johannes Ulen, Yuri Boykov, Vladimir Kolmogorov
Energies with high-order non-submodular interactions have been shown to be very useful in vision due to their high modeling power.