一篇新的基准测试论文介绍了十三种量化图像镜像对称性的方法，比较了经典方法和深度学习方法。研究发现，深度学习模型在单轴和复杂多轴对称性评分方面通常表现更好。然而，一种经典的定向梯度直方图（HOG）描述符表现出了竞争力，其运行速度明显快于深度方法，并且与一些冻结的深度特征提供了可比的结果。 AI
影响 这项研究为对称性评分方法提供了一个基准，表明虽然深度学习表现出色，但像HOG这样的经典方法仍然具有竞争力且高效。
排序理由 该集群包含一篇提出方法基准测试的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2607.08379v1 Announce Type: new Abstract: Quantifying how mirror-symmetric an image is about a given axis (symmetry scoring) underpins applications from visual aesthetics to medical imaging, yet proposed scoring methods have never been compared on a common, statistically gr…
Quantifying how mirror-symmetric an image is about a given axis (symmetry scoring) underpins applications from visual aesthetics to medical imaging, yet proposed scoring methods have never been compared on a common, statistically grounded protocol. We benchmark 13 scoring methods…