15 citations · 26 across the 13 of their papers we have counts for
17 papers
Learning Structure-from-Motion with Graph Attention Networks
Lucas Brynte, José Pedro Iglesias, Carl Olsson +1
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 tho…
Relaxations for Non-Separable Cardinality/Rank Penalties
Carl Olsson, Daniele Gerosa, Marcus Carlsson
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…
On the Tightness of Semidefinite Relaxations for Rotation Estimation
Lucas Brynte, Viktor Larsson, José Pedro Iglesias +2
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 rota…
Monocular Depth Parameterizing Networks
Patrik Persson, Linn Öström, Carl Olsson
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 r…
Accurate Optimization of Weighted Nuclear Norm for Non-Rigid Structure from Motion
José Pedro Iglesias, Carl Olsson, Marcus Valtonen Örnhag
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 b…
A Unified Optimization Framework for Low-Rank Inducing Penalties
Marcus Valtonen Örnhag, Carl Olsson, Anders Heyden
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 fo…
An unbiased approach to low rank recovery
Marcus Carlsson, Daniele Gerosa, Carl Olsson
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-con…
Bias Reduction in Compressed Sensing
Carl Olsson, Marcus Carlsson, Daniele Gerosa
Sparsity and rank functions are important ways of regularizing under-determined linear systems. Optimization of the resulting formulations is made difficult since both these penalt…
Bilinear Parameterization For Differentiable Rank-Regularization
Marcus Valtonen Örnhag, Carl Olsson, Anders Heyden
Low rank approximation is a commonly occurring problem in many computer vision and machine learning applications. There are two common ways of optimizing the resulting models. Eith…
An unbiased approach to compressed sensing
Marcus Carlsson, Daniele Gerosa, Carl Olsson
In compressed sensing a sparse vector is approximately retrieved from an under-determined equation system . Exact retrieval would mean solving a large combinatorial problem w…
A Non-Convex Relaxation for Fixed-Rank Approximation
Carl Olsson, Marcus Carlsson, Erik Bylow
This paper considers the problem of finding a low rank matrix from observations of linear combinations of its elements. It is well known that if the problem fulfills a restricted i…
Rotation Averaging and Strong Duality
Anders Eriksson, Carl Olsson, Fredrik Kahl +1
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. In its convent…
Non-Convex Rank/Sparsity Regularization and Local Minima
Carl Olsson, Marcus Carlsson, Fredrik Andersson +1
This paper considers the problem of recovering either a low rank matrix or a sparse vector from observations of linear combinations of the vector or matrix elements. Recent methods…
Convergence of dual ascent in non-convex/non-differentiable optimization
Fredrik Andersson, Marcus Carlsson, Carl Olsson
We revisit the classical dual ascent algorithm for minimization of convex functionals in the presence of linear constraints, and give convergence results which apply even for non-c…
Convex envelopes for fixed rank approximation
Fredrik Andersson, Marcus Carlsson, Carl Olsson
A convex envelope for the problem of finding the best approximation to a given matrix with a prescribed rank is constructed. This convex envelope allows the usage of traditional op…
Volumetric Bias in Segmentation and Reconstruction: Secrets and Solutions
Yuri Boykov, Hossam Isack, Carl Olsson +1
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…
Simplifying Energy Optimization using Partial Enumeration
Carl Olsson, Johannes Ulen, Yuri Boykov +1
Energies with high-order non-submodular interactions have been shown to be very useful in vision due to their high modeling power. Optimization of such energies, however, is genera…