“…• We show the outstanding performance of EquiSym in reflection symmetry detection on SDRW [27], LDRS [38], and DENDI, and in rotation symmetry detection on DENDI.…”
Section: Introductionmentioning
confidence: 84%
“…Symmetry detection deals with different kinds of symmetric patterns such as reflection axis [1,11,13,14,20,32,37,38,[41][42][43], rotation center [13,20,22,23,32,37,42], and translation lattice [17,24,28,30,35,42,48].…”
Section: Symmetry Detectionmentioning
confidence: 99%
“…Dense prediction. Recently proposed methods [11,13,38,41] predict pixel-wise symmetry scores. Fukushima and Kikuchi [11] build a neural network to extract edges from images and detect reflection symmetry.…”
Section: Symmetry Detectionmentioning
confidence: 99%
“…The simplicity of mathematical concepts of symmetry encouraged early approaches to find keypoint pairs that satisfy pre-defined constraints for symmetry [1,3,32,37,39,43], which leverage hand-crafted local feature descriptors to detect sparse symmetry patterns. Recently, convolutional neural networks (CNNs) have been successfully applied to detect reflection symmetry and have surpassed the previous methods by learning score map regression [13] or symmetric matching [38] from data. The primary challenge in detecting symmetry patterns lies in the fact that a symmetry manifests itself with an arbitrary orientation and perceiving the pattern requires an analysis based on the orientation; a reflection symmetry mirrors itself against an axis with a specific orientation and a rotation symmetry matches its rotated copy with a specific orientation.…”
Section: Introductionmentioning
confidence: 99%
“…We also present a new dataset, DENse and DIverse symmetry (DENDI), for reflection and rotation symmetry detection. DENDI contains real-world images with accurate and clean annotations for reflection and rotation symmetries and mitigates limitations of existing benchmarks [4,12,13,27,38]. First, the reflection symmetry axes are diverse in scale and orientation, while previous datasets mostly focus on the dominant axes of the vertical or horizontal ones.…”
The inherent challenge of detecting symmetries stems from arbitrary orientations of symmetry patterns; a reflection symmetry mirrors itself against an axis with a specific orientation while a rotation symmetry matches its rotated copy with a specific orientation. Discovering such symmetry patterns from an image thus benefits from an equivariant feature representation, which varies consistently with reflection and rotation of the image. In this work, we introduce 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. The proposed network is built end-toend with dihedrally-equivariant layers and trained to output a spatial map for reflection axes or rotation centers. We also present a new dataset, DENse and DIverse symmetry (DENDI), which mitigates limitations of existing benchmarks for reflection and rotation symmetry detection. Experiments show that our method achieves the state of the arts in symmetry detection on LDRS and DENDI datasets.
“…• We show the outstanding performance of EquiSym in reflection symmetry detection on SDRW [27], LDRS [38], and DENDI, and in rotation symmetry detection on DENDI.…”
Section: Introductionmentioning
confidence: 84%
“…Symmetry detection deals with different kinds of symmetric patterns such as reflection axis [1,11,13,14,20,32,37,38,[41][42][43], rotation center [13,20,22,23,32,37,42], and translation lattice [17,24,28,30,35,42,48].…”
Section: Symmetry Detectionmentioning
confidence: 99%
“…Dense prediction. Recently proposed methods [11,13,38,41] predict pixel-wise symmetry scores. Fukushima and Kikuchi [11] build a neural network to extract edges from images and detect reflection symmetry.…”
Section: Symmetry Detectionmentioning
confidence: 99%
“…The simplicity of mathematical concepts of symmetry encouraged early approaches to find keypoint pairs that satisfy pre-defined constraints for symmetry [1,3,32,37,39,43], which leverage hand-crafted local feature descriptors to detect sparse symmetry patterns. Recently, convolutional neural networks (CNNs) have been successfully applied to detect reflection symmetry and have surpassed the previous methods by learning score map regression [13] or symmetric matching [38] from data. The primary challenge in detecting symmetry patterns lies in the fact that a symmetry manifests itself with an arbitrary orientation and perceiving the pattern requires an analysis based on the orientation; a reflection symmetry mirrors itself against an axis with a specific orientation and a rotation symmetry matches its rotated copy with a specific orientation.…”
Section: Introductionmentioning
confidence: 99%
“…We also present a new dataset, DENse and DIverse symmetry (DENDI), for reflection and rotation symmetry detection. DENDI contains real-world images with accurate and clean annotations for reflection and rotation symmetries and mitigates limitations of existing benchmarks [4,12,13,27,38]. First, the reflection symmetry axes are diverse in scale and orientation, while previous datasets mostly focus on the dominant axes of the vertical or horizontal ones.…”
The inherent challenge of detecting symmetries stems from arbitrary orientations of symmetry patterns; a reflection symmetry mirrors itself against an axis with a specific orientation while a rotation symmetry matches its rotated copy with a specific orientation. Discovering such symmetry patterns from an image thus benefits from an equivariant feature representation, which varies consistently with reflection and rotation of the image. In this work, we introduce 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. The proposed network is built end-toend with dihedrally-equivariant layers and trained to output a spatial map for reflection axes or rotation centers. We also present a new dataset, DENse and DIverse symmetry (DENDI), which mitigates limitations of existing benchmarks for reflection and rotation symmetry detection. Experiments show that our method achieves the state of the arts in symmetry detection on LDRS and DENDI datasets.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.