用几何先验提升多视角图像匹配精度，无需复杂训练数据。
Multi-view dense image matching with similarity learning and geometry priors
- 引入在线几何先验，结合极线与单应性校正生成感知几何特征。
- 在航空与卫星影像上表现更优，尤其在不同采样距离下泛化能力强。
- 可直接接入主流图像匹配流程，适用于多分辨率影像处理。
我们提出MV-DeepSimNets，一套用于多视角相似性学习的深度神经网络，利用极线几何进行训练。方法引入在线几何先验，以刻画像素间关系，沿极线或通过单应性校正实现。该机制使原始图像生成几何感知特征，并通过平面扫掠投影至候选深度假设。几何预处理有效适配基于极线的特征，提升多视角重建性能，且无需繁琐的多视角训练数据构建。通过聚合学习到的相似性，构建并正则化代价体，显著改善传统密集匹配的表面重建效果。在航空与卫星影像上，相比领先相似性学习网络和端到端回归模型，本方法在跨不同地面采样距离的泛化能力上表现卓越。该流程已集成至MicMac软件，可无缝嵌入标准多分辨率图像匹配流程。
原文摘要 · Abstract (English)
We introduce MV-DeepSimNets, a comprehensive suite of deep neural networks designed for multi-view similarity learning, leveraging epipolar geometry for training. Our approach incorporates an online geometry prior to characterize pixel relationships, either along the epipolar line or through homography rectification. This enables the generation of geometry-aware features from native images, which are then projected across candidate depth hypotheses using plane sweeping. Our method geometric preconditioning effectively adapts epipolar-based features for enhanced multi-view reconstruction, without requiring the laborious multi-view training dataset creation. By aggregating learned similarities, we construct and regularize the cost volume, leading to improved multi-view surface reconstruction over traditional dense matching approaches. MV-DeepSimNets demonstrates superior performance against leading similarity learning networks and end-to-end regression models, especially in terms of generalization capabilities across both aerial and satellite imagery with varied ground sampling distances. Our pipeline is integrated into MicMac software and can be readily adopted in standard multi-resolution image matching pipelines.
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。