Search Results for author:
Found 19 papers, 3 papers with code
Learning Structure-from-Motion with Graph Attention Networks
In this paper we tackle the problem of learning Structure-from-Motion (SfM) through the use of graph attention networks.
expOSE: Accurate Initialization-Free Projective Factorization Using Exponential Regularization
The recently introduced factorization-based pOSE methods formulate a surrogate for the bundle adjustment error without reliance on good initialization.
Revisiting the P3P Problem
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.
A Quasiconvex Formulation for Radial Cameras
In this paper we study structure from motion problems for 1D radial cameras.
Bilinear Parameterization for Non-Separable Singular Value Penalties
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.
On the Tightness of Semidefinite Relaxations for Rotation Estimation
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.
Radial Distortion Invariant Factorization for Structure From Motion
Factorization methods are frequently used for structure from motion problems (SfM).
Monocular Depth Parameterizing Networks
For this purpose we propose a network structure that given an image provides a parameterization of a set of depth maps with feasible shapes.
Accurate Optimization of Weighted Nuclear Norm for Non-Rigid Structure from Motion
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.
A Unified Optimization Framework for Low-Rank Inducing Penalties
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
Bilinear Parameterization For Differentiable Rank-Regularization
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.
Compact Matrix Factorization With Dependent Subspaces
This imposes constraints on the matrix elements which allow for estimation of missing entries.
Rotation Averaging and Strong Duality
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.
Optimal Relative Pose With Unknown Correspondences
Previous work on estimating the epipolar geometry of two views relies on being able to reliably match feature points based on appearance.
Minimizing the Maximal Rank
In the latter case, matrices are divided into sub-matrices and the envelope is computed for each sub-block individually.
Practical Robust Two-View Translation Estimation
Outliers pose a problem in all real structure from motion systems.
Volumetric Bias in Segmentation and Reconstruction: Secrets and Solutions
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.
In Defense of 3D-Label Stereo
Our theoretical and experimental results demonstrate advantages over state-of-the-art methods for 2nd order smoothness stereo.
Simplifying Energy Optimization using Partial Enumeration
Energies with high-order non-submodular interactions have been shown to be very useful in vision due to their high modeling power.
