在未知相机和表面形状下，实时学习图像间点对应关系
Online Learning of Correspondences between Images
- 用密度差异优化点对应映射，无需3D信息
- 每帧更新映射，实现快速收敛与高精度
- 适合动态场景下实时匹配，性能超越现有方法
本文提出一种迭代学习图像序列中点对应关系的新方法。三维空间中移动的点被投影到两幅图像上，给定任一视图中的点，目标是确定其在另一视图中的对应位置。由于投影几何、畸变及表面形状均未知，传统方法依赖全局优化或透视投影下的基础矩阵。本文提出一种适用于一般成像几何的迭代解法，基于奈曼卡方散度优化估计位置与真实位置的概率密度间的差异。密度通过基函数方法表示为通道向量，每对新图像更新映射，实现快速收敛与高精度。算法可在实时运行，并在多项实验中优于当前最优方法。
原文摘要 · Abstract (English)
We propose a novel method for iterative learning of point correspondences between image sequences. Points moving on surfaces in 3D space are projected into two images. Given a point in either view, the considered problem is to determine the corresponding location in the other view. The geometry and distortions of the projections are unknown as is the shape of the surface. Given several pairs of point-sets but no access to the 3D scene, correspondence mappings can be found by excessive global optimization or by the fundamental matrix if a perspective projective model is assumed. However, an iterative solution on sequences of point-set pairs with general imaging geometry is preferable. We derive such a method that optimizes the mapping based on Neyman's chi-square divergence between the densities representing the uncertainties of the estimated and the actual locations. The densities are represented as channel vectors computed with a basis function approach. The mapping between these vectors is updated with each new pair of images such that fast convergence and high accuracy are achieved. The resulting algorithm runs in real-time and is superior to state-of-the-art methods in terms of convergence and accuracy in a number of experiments.
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。