ARD-REFSM：通过非对称去噪与旋转等变性增强反射对称检测

中文摘要 AI 辅助

反射对称检测仍面临挑战，原因在于非对称区域的干扰以及对称模式的任意朝向。非对称区域会引入背景杂波，破坏对称模式匹配，而传统卷积神经网络缺乏旋转等变性，导致在旋转变换下特征表示不一致。为解决这些问题，我们提出非对称区域去噪（Asymmetric Region Denoising, ARD）模块与旋转等变特征相似度匹配（Rotation Equivariant Feature Similarity Matching, REFSM）模块。ARD模块抑制非对称干扰以优化对称模式，REFSM模块通过原始图像与旋转图像间的特征相似度匹配增强旋转等变性。具体而言，我们的双输入REFSM框架利用旋转损失最大化原始图像与旋转图像得分图的一致性，从而实现旋转等变对称轴的精确预测。此外，我们引入新的基准数据集GMSYM，该数据集将图像划分为多样场景并融入各类干扰，以解决现有反射对称检测基准的局限性。在四个标准数据集（DENDI、NYU、LDRS、SDRW）及我们提出的GMSYM数据集上开展的大量实验表明，所提方法在准确率与鲁棒性方面均达到了当前最优性能。

英文摘要

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. Specifically, our dual-input REFSM framework leverages rotation loss to maximize consistency between the score maps of original and rotated images, thereby enabling precise prediction of rotation-equivariant symmetry axes. Furthermore, we introduce GMSYM, a new benchmark dataset that categorizes images into diverse scenarios and incorporates various interferences to address the limitations of existing reflection symmetry detection benchmarks. Extensive experiments on four standard datasets (DENDI, NYU, LDRS, SDRW) and our proposed GMSYM dataset demonstrate that our method achieves state-of-the-art performance in both accuracy and robustness.

发表机构

• Guangdong Laboratory of Artificial Intelligence and Digital Economy(SZ)（广东省人工智能与数字经济实验室（深圳））
• College of Computer Science and Software Engineering, Shenzhen University（深圳大学计算机与软件学院）
• School of Information Technology, Carleton University（卡尔顿大学信息技术学院）

机构由 AI 辅助整理，请以论文原文为准。