%AXie, Youye%ATang, Yingheng%ATang, Gongguo%AHoff, William%Anull Ed.%D2021%I %K %MOSTI ID: 10253358 %PMedium: X %TLearning To Find Good Correspondences Of Multiple Objects %XGiven a set of 3D to 2D putative matches, labeling the correspondences as inliers or outliers plays a critical role in a wide range of computer vision applications including the Perspective-n-Point (PnP) and object recognition. In this paper, we study a more generalized problem which allows the matches to belong to multiple objects with distinct poses. We propose a deep architecture to simultaneously label the correspondences as inliers or outliers and classify the inliers into multiple objects. Specifically, we discretize the 3D rotation space into twenty convex cones based on the facets of a regular icosahedron. For each facet, a facet classifier is trained to predict the probability of a correspondence being an inlier for a pose whose rotation normal vector points towards this facet. An efficient RANSAC-based post-processing algorithm is also proposed to further process the prediction results and detect the objects. Experiments demonstrate that our method is very efficient compared to existing methods and is capable of simultaneously labeling and classifying the inliers of multiple objects with high precision. Country unknown/Code not availablehttps://doi.org/10.1109/ICPR48806.2021.9413319OSTI-MSA