Axis-level Symmetry Detection with Group-Equivariant Representation
By: Wongyun Yu, Ahyun Seo, Minsu Cho
Potential Business Impact:
Finds exact lines and points of symmetry.
Symmetry is a fundamental concept that has been extensively studied, yet detecting it in complex scenes remains a significant challenge in computer vision. Recent heatmap-based approaches can localize potential regions of symmetry axes but often lack precision in identifying individual axes. In this work, we propose a novel framework for axis-level detection of the two most common symmetry types-reflection and rotation-by representing them as explicit geometric primitives, i.e. lines and points. Our method employs a dual-branch architecture that is equivariant to the dihedral group, with each branch specialized to exploit the structure of dihedral group-equivariant features for its respective symmetry type. For reflection symmetry, we introduce orientational anchors, aligned with group components, to enable orientation-specific detection, and a reflectional matching that measures similarity between patterns and their mirrored counterparts across candidate axes. For rotational symmetry, we propose a rotational matching that compares patterns at fixed angular intervals to identify rotational centers. Extensive experiments demonstrate that our method achieves state-of-the-art performance, outperforming existing approaches.
Similar Papers
Leveraging 3D Geometric Priors in 2D Rotation Symmetry Detection
CV and Pattern Recognition
Finds repeating shapes in pictures, even from different angles.
Probing Equivariance and Symmetry Breaking in Convolutional Networks
CV and Pattern Recognition
Makes AI better at understanding shapes and patterns.
To Augment or Not to Augment? Diagnosing Distributional Symmetry Breaking
Machine Learning (CS)
Finds when computer "seeing" tricks work.