Beyond Planar Symmetry: Modeling human perception of reflection and rotation symmetries in the wild
원문 초록
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 deep-learning 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 consistent symmetry-labels from more than 400 human observers. We employ novel methods to convert discrete human labels into symmetry heatmaps, capture symmetry densely in an image and quantitatively evaluate Sym-NET against multiple existing computer vision algorithms. On CVPR 2013 symmetry competition testsets and unseen MS-COCO photos, Sym-NET significantly outperforms all other competitors. Beyond mathematically well-defined symmetries on a plane, Sym-NET demonstrates abilities to identify viewpoint-varied 3D symmetries, partially occluded symmetrical objects, and symmetries at a semantic level.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Scattering Spectra Models for Physics
Hamiltonian Neural Networks with Automatic Symmetry Detection
Signal enhancement for two-dimensional cryo-EM data processing
Reflection and Rotation Symmetry Detection via Equivariant Learning
Using Machine Learning to Detect Rotational Symmetries from Reflectional Symmetries in 2D Images
Data Augmentation through Expert-guided Symmetry Detection to Improve Performance in Offline Reinforcement Learning
토론
이 논문과 연결된 포럼 글이 아직 없습니다.