ARD-REFSM: Enhancing Reflection Symmetry Detection with Asymmetric Denoising and Rotation Equivariance 文章

ArXiv CS.CV2026-07-31PAPERen作者: Dongfu Yin, Rourou Su, Cong Zhao, Fei Yu

详细信息

来源站点
ArXiv CS.CV
作者
Dongfu Yin, Rourou Su, Cong Zhao, Fei Yu
文章类型
PAPER
语言
en
发布日期
2026-07-31

摘要

arXiv:2607.27927v1 Announce Type: new Abstract: Reflection symmetry detection remains challenging due to interference from asymmetric regions and arbitrary orientations of symmetric patterns. Asymmetric regions introduce background clutter that disrupts symmetric pattern matching, whereas conventional convolutional neural networks lack rotation equivariance, leading to inconsistent feature representations under rotational transformations. To address these issues, we propose an Asymmetric Region Denoising (ARD) module and a Rotation Equivariant Feature Similarity Matching (REFSM) module. The ARD module suppresses asymmetric interference to refine symmetric patterns, while the REFSM module enhances rotation equivariance through feature similarity matching between original and rotated images.

相关事件

暂无数据

相关公司查看全部 (1)

相关人物

暂无数据