Coplanar Repeats by Energy Minimization

@article{Pritts2016CoplanarRB,
  title={Coplanar Repeats by Energy Minimization},
  author={James Pritts and Denys Rozumnyi and M. Pawan Kumar and Ondřej Chum},
  journal={ArXiv},
  year={2016},
  volume={abs/1711.09432}
}
This paper proposes an automated method to detect, group and rectify arbitrarily-arranged coplanar repeated elements via energy minimization. The proposed energy functional combines several features that model how planes with coplanar repeats are projected into images and captures global interactions between different coplanar repeat groups and scene planes. An inference framework based on a recent variant of $\alpha$-expansion is described and fast convergence is demonstrated. We compare the… 

Figures and Tables from this paper

Rectification from Radially-Distorted Scales
TLDR
This paper introduces the first minimal solvers that jointly estimate lens distortion and affine rectification from repetitions of rigidly-transformed coplanar local features and demonstrates superior robustness to noise compared to the state of the art.
Minimal Solvers for Rectifying from Radially-Distorted Scales and Change of Scales
TLDR
The first minimal solvers that jointly estimate lens distortion and affine rectification from the image of rigidly-transformed coplanar features are introduced and superior robustness to noise compared to the state of the art is demonstrated.
Radially-Distorted Conjugate Translations
TLDR
This paper introduces the first minimal solvers that jointly solve for affine-rectification and radial lens distortion from coplanar repeated patterns and demonstrates high-accuracy undistortion and rectification on noisy measurements.
Minimal Solvers for Single-View Lens-Distorted Camera Auto-Calibration
This paper proposes minimal solvers that use combinations of imaged translational symmetries and parallel scene lines to jointly estimate lens undistortion with either affine rectification or focal
Consistency functional map propagation for repetitive patterns
  • Hao Wang
  • Computer Science
    J. Electronic Imaging
  • 2017
TLDR
A consistency functional map propagation (CFMP) algorithm that extends the functional map with dynamic propagation is proposed to address the repetitive patterns due to the large photometric and geometric variations.
Single-Image Depth Prediction Makes Feature Matching Easier
TLDR
It is shown that CNN-based depths inferred from single RGB images are quite helpful, despite their flaws, and allow us to pre-warp images and rectify perspective distortions, to significantly enhance SIFT and BRISK features, enabling more good matches, even when cameras are looking at the same scene but in opposite directions.
Minimal Solvers for Rectifying From Radially-Distorted Conjugate Translations
This paper introduces minimal solvers that jointly solve for radial lens undistortion and affine-rectification using local features extracted from the image of coplanar translated and reflected scene

References

SHOWING 1-10 OF 26 REFERENCES
Detection, Rectification and Segmentation of Coplanar Repeated Patterns
This paper presents a novel and general method for the detection, rectification and segmentation of imaged coplanar repeated patterns. The only assumption made of the scene geometry is that repeated
Geometric Grouping of Repeated Elements within Images
TLDR
It is shown that structures that repeat in the world are related by particular parametrized transformations in perspective images, and these image transformations provide powerful grouping constraints, and can be used at the heart of hypothesize and verify grouping algorithms.
Detecting Large Repetitive Structures with Salient Boundaries
TLDR
A novel robust and efficient framework to analyze large repetitive structures in urban scenes that finds the salient boundaries of the repeating elements even when the repetition exists along only one direction.
The multiRANSAC algorithm and its application to detect planar homographies
TLDR
The algorithm presented in this paper, called multiRANSAC, on average performs better than traditional approaches based on the sequential application of a standard RANSAC algorithm followed by the removal of the detected set of inliers.
Planar Affine Rectification from Change of Scale
TLDR
The proposed method is simple to implement and without parameters; linear and thus supporting (algebraic) least squares solutions; and general, without restrictions on either the shape of the corresponding features or their mutual position.
Translation-Symmetry-Based Perceptual Grouping with Applications to Urban Scenes
TLDR
This work proposes a novel mid-level visual feature detector where the visual elements are grouped based on the 2D translation subgroup of a wallpaper pattern, which can detect multiple, semantically relevant 2D lattices in a scene simultaneously, achieving an effective translation-symmetry-based segmentation.
Fast Approximate Energy Minimization with Label Costs
TLDR
The main algorithmic contribution is an extension of α-expansion that also optimizes “label costs” with well-characterized optimality bounds, which has a natural interpretation as minimizing description length (MDL) and sheds light on classical algorithms like K-means and expectation-maximization (EM).
Symmetry Detection from RealWorld Images Competition 2013: Summary and Results
TLDR
A US NSF funded symmetry detection algorithm competition as a workshop affiliated with the Computer Vision and Pattern Recognition (CVPR) Conference, 2013 sets a more complete benchmark for computer vision symmetry detection algorithms.
Energy-Based Geometric Multi-model Fitting
TLDR
The proposed PEaRL combines model sampling from data points as in RANSAC with iterative re-estimation of inliers and models’ parameters based on a global regularization functional and converges to a good quality local minimum of the energy automatically selecting a small number of models that best explain the whole data set.
Metric rectification for perspective images of planes
  • D. Liebowitz, Andrew Zisserman
  • Mathematics
    Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231)
  • 1998
TLDR
The novel contributions are that in a stratified context the various forms of providing metric information can be represented as circular constraints on the parameters of an affine transformation of the plane, providing a simple and uniform framework for integrating constraints.
...
1
2
3
...