2017 ICCV Challenge: Detecting Symmetry in the Wild

Funk, Christopher; Lee, Seungkyu; Oswald, Martin R.; Tsogkas, Stavros; Shen, Wei; Cohen, Andrea; Dickinson, Sven; Liu, Yanxi

doi:10.1109/iccvw.2017.198

Cited by 54 publications

(74 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where y ∈ R l is a vector of l monomials in the remaining n − k unknowns (i.e., monomials of unknowns not appearing in M). A nontrivial solution to (2) exists only if M is rank-deficient. The problem has been simplified since the n − k unknowns in y are eliminated from solving det M = 0.…”

Section: The Hidden Variable Trickmentioning

confidence: 99%

Minimal Solvers for Rectifying from Radially-Distorted Scales and Change of Scales

et al. 2020

View full text Add to dashboard Cite

This paper introduces minimal solvers that jointly solve for affine-rectification and radial lens undistortion from the image of translated and reflected coplanar features. The proposed solvers use the invariant that the affine-rectified image of the meet of the joins of radially-distorted conjugately-translated point correspondences is on the line at infinity. The hidden-variable trick from algebraic geometry is used to reformulate and simplify the constraints so that the generated solvers are stable, small and fast. Multiple solvers are proposed to accommodate various local feature types and sampling strategies, and, remarkably, three of the proposed solvers can recover rectification and lens undistortion from only one radially-distorted conjugately-translated affine-covariant region correspondence. Synthetic and real-image experiments confirm that the proposed solvers demonstrate superior robustness to noise compared to the state of the art. Accurate rectifications on imagery taken with narrow to fisheye field-of-view lenses demonstrate the wide applicability of the proposed method. The method is fully automatic.

show abstract

Section: The Hidden Variable Trickmentioning

confidence: 99%

Minimal Solvers for Rectifying from Radially-Distorted Scales and Change of Scales

et al. 2020

View full text Add to dashboard Cite

show abstract

“…We used the automatic generator from Larsson et al [12] to make the polynomial solvers for the three input configurations (222, 32,4). The solver corresponding to each input configuration is denoted H 222 lλ, H 32 lλ, and H 4 lλ, respectively.…”

Section: Creating the Solversmentioning

confidence: 99%

“…The solvers are fast and robust to noisy feature detections, so they work well in robust estimation frameworks like RANSAC [3]. The proposed work is applicable for several important computer vision tasks including symmetry detection [4], inpainting [5], and single-view 3D reconstruction [6].…”

Section: Introductionmentioning

confidence: 99%

Rectification from Radially-Distorted Scales

Pritts

Kúkelová

Larsson

et al. 2019

Computer Vision – ACCV 2018

View full text Add to dashboard Cite

This paper introduces the first minimal solvers that jointly estimate lens distortion and affine rectification from repetitions of rigidly-transformed coplanar local features. The proposed solvers incorporate lens distortion into the camera model and extend accurate rectification to wide-angle images that contain nearly any type of coplanar repeated content. We demonstrate a principled approach to generating stable minimal solvers by the Gröbner basis method, which is accomplished by sampling feasible monomial bases to maximize numerical stability. Synthetic and real-image experiments confirm that the solvers give accurate rectifications from noisy measurements if used in a RANSAC-based estimator. The proposed solvers demonstrate superior robustness to noise compared to the state of the art. The solvers work on scenes without straight lines and, in general, relax strong assumptions about scene content made by the state of the art. Accurate rectifications on imagery taken with narrow focal length to fisheye lenses demonstrate the wide applicability of the proposed method. The method is automatic, and the code is published at https://github.com/prittjam/repeats.

show abstract

“…We use the detected pairs mirror symmetric pixels in the Section III-A to detect the symmetry axes of the reflective symmetric objects present in the input image. We represent the detected pairs of mirror symmetric pixels as the collection of sets {P i } k i=1 such that each set P i contains pairs of mirror [62], [63], [64], [65], [36], [35], AND PROPOSED METHOD ON THE IMAGES OF THE DATASET [58]. and is perpendicular to the vector x j − x j .…”

Section: A Symmetry Axis Detectionmentioning

confidence: 99%

“…Therefore, probability of not selecting the approximate mirror reflection pixel of a pixel under consideration in h attempts is 1 − u 2 In Fig. 3, we present a few results of symmetry detection on the images from the dataset [58].…”

mentioning

confidence: 99%

SymmSLIC: Symmetry Aware Superpixel Segmentation

Nagar

Raman

2017

2017 IEEE International Conference on Computer Vision Workshops (ICCVW)

View full text Add to dashboard Cite

Over-segmentation of an image into superpixels has become a useful tool for solving various problems in image processing and computer vision. Reflection symmetry is quite prevalent in both natural and man-made objects and is an essential cue in understanding and grouping the objects in natural scenes. Existing algorithms for estimating superpixels do not preserve the reflection symmetry of an object which leads to different sizes and shapes of superpixels across the symmetry axis. In this work, we propose an algorithm to over-segment an image through the propagation of reflection symmetry evident at the pixel level to superpixel boundaries. In order to achieve this goal, we first find the reflection symmetry in the image and represent it by a set of pairs of pixels which are mirror reflections of each other. We partition the image into superpixels while preserving this reflection symmetry through an iterative algorithm. We compare the proposed method with state-of-the-art superpixel generation methods and show the effectiveness in preserving the size and shape of superpixel boundaries across the reflection symmetry axes. We also present two applications, symmetry axes detection and unsupervised symmetric object segmentation, to illustrate the effectiveness of the proposed approach.

show abstract

2017 ICCV Challenge: Detecting Symmetry in the Wild

Cited by 54 publications

References 39 publications

Minimal Solvers for Rectifying from Radially-Distorted Scales and Change of Scales

Minimal Solvers for Rectifying from Radially-Distorted Scales and Change of Scales

Rectification from Radially-Distorted Scales

SymmSLIC: Symmetry Aware Superpixel Segmentation

Contact Info

Product

Resources

About