Beyond Planar Symmetry: Modeling Human Perception of Reflection and Rotation Symmetries in the Wild

  title={Beyond Planar Symmetry: Modeling Human Perception of Reflection and Rotation Symmetries in the Wild},
  author={Christopher Funk and Yanxi Liu},
  journal={2017 IEEE International Conference on Computer Vision (ICCV)},
  • Christopher Funk, Yanxi Liu
  • Published 11 April 2017
  • Computer Science
  • 2017 IEEE International Conference on Computer Vision (ICCV)
Humans take advantage of real world symmetries for various tasks, yet capturing their superb symmetry perception mechanism with a computational model remains elusive. Motivated by a new study demonstrating the extremely high inter-person accuracy of human perceived symmetries in the wild, we have constructed the first deeplearning neural network for reflection and rotation symmetry detection (Sym-NET), trained on photos from MS-COCO (Microsoft-Common Object in COntext) dataset with nearly 11K… 

Figures and Tables from this paper

Reflection and Rotation Symmetry Detection via Equivariant Learning

This work introduces a group-equivariant convolutional network for symmetry detection, dubbed EquiSym, which leverages equivariant feature maps with respect to a dihedral group of reflection and rotation.

Learning to Discover Reflection Symmetry via Polar Matching Convolution

A new convolutional technique is introduced, dubbed the polar matching convolution, which leverages a polar feature pooling, a self-similarity encoding, and a systematic kernel design for axes of different angles to discover symmetry patterns from real-world images.

NeRD: Neural 3D Reflection Symmetry Detector

NeRD, a Neural 3D Reflection Symmetry Detector, which combines the strength of learning-based recognition and geometry-based reconstruction to accurately recover the normal direction of objects’ mirror planes and is used to improve the performance of downstream tasks such as pose estimation and depth map regression.

Combining Appearance and Gradient Information for Image Symmetry Detection

This work addresses the challenging problem of reflection symmetry detection in unconstrained environments by proposing the design of a stable metric that extracts subsets of consistently oriented candidate segments, whenever the underlying 2D signal appearance exhibits definite near symmetric correspondences.

2017 ICCV Challenge: Detecting Symmetry in the Wild

This report provides a detailed summary of the evaluation methodology for each type of symmetry detection algorithm validated, and demonstrates and analyzes quantified detection results in terms of precision-recall curves and F-measures for all algorithms evaluated.

Using Machine Learning to Detect Rotational Symmetries from Reflectional Symmetries in 2D Images

This paper proposes postprocessing improvements to find localised symmetries in images, improve the selection of detected symmetryetries and identify another symmetry type (rotational) and contributes a machine learning model which detects rotational asymmetries based on provided reflection symmetry axis pairs.

Symmetry Perception by Deep Networks: Inadequacy of Feed-Forward Architectures and Improvements with Recurrent Connections

It is found that recurrent architectures are capable of learning to perceive symmetry by decomposing the longrange spatial dependencies into a sequence of local operations, that are reusable for novel images and suggest that recurrent connections likely play an important role in symmetry perception in artificial systems, and possibly, biological ones too.

Improving Machine Vision Using Human Perceptual Representations: The Case of Planar Reflection Symmetry for Object Classification

  • R. PramodS. Arun
  • Computer Science
    IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2022
The results show that machine vision can be improved by discovering and fixing systematic differences from human vision, and augmenting a state-of-the-art convolutional neural network with planar/reflection symmetry scores along multiple axes produced significant improvements in classification accuracy.

Recurrently Estimating Reflective Symmetry Planes from Partial Pointclouds

This paper presents an alternative novel encoding that instead slices the data along the height dimension and passes it sequentially to a 2D convolutional recurrent regression scheme, allowing for end-to-end accurate and fast processing of both full and partial scans of symmetric objects.

Data-efficient learning for 3D mirror symmetry detection

A geometry-inspired deep learning method for detecting 3D mirror plane from single-view images by explicitly adding3D mirror geometry into learning as an inductive prior and designs multi-stage spherical convolutions to identify the optimal mirror plane in a coarse-to-fine manner.



Deep Symmetry Networks

Deep symmetry networks (symnets), a generalization of convnets that forms feature maps over arbitrary symmetry groups that uses kernel-based interpolation to tractably tie parameters and pool over symmetry spaces of any dimension are introduced.

Symmetry reCAPTCHA

This systematic study reveals significant difference between human labeled (reflection and rotation) symmetries on photos and the output of computer vision algorithms on the same photo set, and proposes a novel symmetry-based Turing test to exploit this human-machine symmetry perception gap.

Symmetry Detection from RealWorld Images Competition 2013: Summary and Results

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.

Detection and Segmentation of 2D Curved Reflection Symmetric Structures

This work proposes a complete approach that links the detection of curved reflection symmetries to produce symmetry-constrained segments of structures/regions in real images with clutter to enforce global symmetrical consistency in the final segmentation.

Human Symmetry Perception and Its Computational Analysis

Contents: Part I:Introduction. C.W. Tyler, Human Symmetry Perception. Part II:Empirical Evaluation of Symmetry Perception. J. Wagemans, Detection of Visual Symmetries. P. Wenderoth, The Role of

Skewed Rotation Symmetry Group Detection

This work proposes a frieze-expansion (FE) method that transforms rotation symmetry group detection into a simple, 1D translation symmetry detection problem, and proposes a pair of rotational symmetry saliency maps, complemented by a local feature method.

Curved Glide-Reflection Symmetry Detection

The concept of bilateral reflection symmetry to curved glide-reflection symmetry in 2D euclidean space is generalized, such that classic reflection symmetry becomes one of its six special cases, and a local feature-based approach for curved gliding symmetry detection from real, unsegmented 2D images is proposed.

Computational Symmetry in Computer Vision and Computer Graphics

Recognizing the fundamental relevance and group theory of symmetry has the potential to play an important role in computational sciences.

DeepFace: Closing the Gap to Human-Level Performance in Face Verification

This work revisits both the alignment step and the representation step by employing explicit 3D face modeling in order to apply a piecewise affine transformation, and derive a face representation from a nine-layer deep neural network.