Techniques for dense semantic correspondence have provided limited ability to deal with the geometric variations that commonly exist between semantically similar images. While variations due to scale and rotation have been examined, there is a lack of practical solutions for more complex deformations such as affine transformations because of the tremendous size of the associated solution space. To address this problem, we present a discrete-continuous transformation matching (DCTM) framework where dense affine transformation fields are inferred through a discrete label optimization in which the labels are iteratively updated via continuous regularization. In this way, our approach draws solutions from the continuous space of affine transformations in a manner that can be computed efficiently through constant-time edge-aware filtering and a proposed affine-varying CNN-based descriptor. Furthermore, leveraging correspondence consistency and confidence-guided filtering in each iteration facilitates the convergence of our method. Experimental results show that this model outperforms the state-of-the-art methods for dense semantic correspondence on various benchmarks and applications.

中文翻译：

---

密集语义对应的离散连续变换匹配


密集语义对应技术提供了有限的能力来处理语义相似图像之间通常存在的几何变化。虽然已经检查了由于尺度和旋转引起的变化，但由于相关解空间的巨大尺寸，缺乏针对更复杂的变形（例如仿射变换）的实用解决方案。为了解决这个问题，我们提出了一个离散连续变换匹配（DCTM）框架，其中通过离散标签优化推断密集仿射变换场，其中标签通过连续正则化迭代更新。通过这种方式，我们的方法从仿射变换的连续空间中得出解决方案，其方式可以通过恒定时间边缘感知过滤和提出的基于仿射变化 CNN 的描述符进行有效计算。此外，在每次迭代中利用对应一致性和置信引导过滤有助于我们方法的收敛。实验结果表明，该模型在各种基准和应用程序上优于最先进的密集语义对应方法。