针对全景图像畸变问题，提出新型稠密匹配方法提升对应点精度。
EDM: Equirectangular Projection-Oriented Dense Kernelized Feature Matching
- 基于球面相机模型与测地流优化，缓解等距投影畸变。
- 在Matterport3D和Stanford2D3D上AUC@5°分别提升26.72和42.62。
- 适用于全景视觉匹配，适合自动驾驶与三维重建场景。
我们提出首个基于学习的稠密匹配算法EDM（Equirectangular Projection-Oriented Dense Kernelized Feature Matching），专为全景图像设计。等距投影（ERP）图像具有大视场，适合实现跨图像的全面对应关系，但存在显著畸变。为此，我们利用球面相机模型与测地流精炼机制，在稠密匹配中进行补偿。进一步提出基于特征网格3D笛卡尔坐标的球面位置嵌入，并在精炼过程中引入球面与笛卡尔坐标系间的双向变换，借助单位球体提升匹配性能。实验表明，该方法在Matterport3D和Stanford2D3D数据集上的AUC@5°分别提升26.72和42.62。
原文摘要 · Abstract (English)
We introduce the first learning-based dense matching algorithm, termed Equirectangular Projection-Oriented Dense Kernelized Feature Matching (EDM), specifically designed for omnidirectional images. Equirectangular projection (ERP) images, with their large fields of view, are particularly suited for dense matching techniques that aim to establish comprehensive correspondences across images. However, ERP images are subject to significant distortions, which we address by leveraging the spherical camera model and geodesic flow refinement in the dense matching method. To further mitigate these distortions, we propose spherical positional embeddings based on 3D Cartesian coordinates of the feature grid. Additionally, our method incorporates bidirectional transformations between spherical and Cartesian coordinate systems during refinement, utilizing a unit sphere to improve matching performance. We demonstrate that our proposed method achieves notable performance enhancements, with improvements of +26.72 and +42.62 in AUC@5° on the Matterport3D and Stanford2D3D datasets.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。