Not identical but similar objects are ubiquitous in our world, ranging from four-legged animals such as dogs and cats to cars of different models and flowers of various colors. This study addresses a novel task of matching such non-identical objects at the pixel level. We propose a weighting scheme of descriptors, Semantic Enhancement Weighting (SEW), that incorporates semantic information from object detectors into existing sparse feature matching methods, extending their targets from identical objects captured from different perspectives to semantically similar objects. The experiments show successful matching between non-identical objects in various cases, including in-class design variations, class discrepancy, and domain shifts (e.g., photo vs. drawing and image corruptions). The code is available at https://github.com/Circ-Leaf/NIOM .

翻译：非相同但相似的物体在我们的世界中无处不在，从四足动物（如狗和猫）到不同型号的汽车以及各种颜色的花朵。本研究解决了一项新颖的任务：在像素级别匹配此类非相同物体。我们提出了一种描述符加权方案——语义增强加权（SEW），该方案将来自物体检测器的语义信息整合到现有的稀疏特征匹配方法中，从而将其目标从不同视角捕获的相同物体扩展到语义相似的物体。实验表明，该方法在多种情况下成功实现了非相同物体之间的匹配，包括类内设计变化、类别差异以及域偏移（例如照片与绘图以及图像损坏）。代码可在 https://github.com/Circ-Leaf/NIOM 获取。