DeepSim-Nets：用于立体图像匹配的深度相似性网络
DeepSim-Nets: Deep Similarity Networks for Stereo Image Matching
AI总结：
本文提出 DeepSim-Nets 多尺度相似性学习架构，通过对比损失在大图像块上学习像素级匹配特征，并结合样本挖掘提升鲁棒性，在航空与卫星数据上优于混合和端到端方法。
摘要：
我们提出了三种多尺度相似性学习架构，即 DeepSim 网络。这些模型通过对比损失学习像素级匹配，并且与所考虑场景的几何结构无关。我们通过学习一次性密集分配极线对的所有对应像素，在混合方法和端到端方法之间建立了一个中间地带。我们的特征在大图像块上学习，以具有表现力并捕获场景更广泛的上下文。我们还证明了精心设计的样本挖掘可以增强预测相似性的整体鲁棒性，并提高在辐射测量上均匀区域的性能。我们在航空和卫星数据集上进行了实验。我们的 DeepSim-Nets 优于基线混合方法，并且比端到端方法更好地泛化到未见过的场景几何结构。我们灵活的架构可以很容易地用于标准的多分辨率图像匹配流程中。
英文摘要：
We present three multi-scale similarity learning architectures, or DeepSim networks. These models learn pixel-level matching with a contrastive loss and are agnostic to the geometry of the considered scene. We establish a middle ground between hybrid and end-to-end approaches by learning to densely allocate all corresponding pixels of an epipolar pair at once. Our features are learnt on large image tiles to be expressive and capture the scene's wider context. We also demonstrate that curated sample mining can enhance the overall robustness of the predicted similarities and improve the performance on radiometrically homogeneous areas. We run experiments on aerial and satellite datasets. Our DeepSim-Nets outperform the baseline hybrid approaches and generalize better to unseen scene geometries than end-to-end methods. Our flexible architecture can be readily adopted in standard multi-resolution image matching pipelines.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
