Unsupervised matching in fine-grained datasets for single view object reconstruction

摘要

A computer-implemented method for training a deep learning network is presented. The method includes receiving a first image and a second image, mining exemplar thin-plate spline (TPS) to determine transformations for generating point correspondences between the first and second images, using artificial point correspondences to train the deep neural network, learning and using the TPS transformation output through a spatial transformer, and applying heuristics for selecting an acceptable set of images to match for accurate reconstruction. The deep learning network learns to warp points in the first image to points in the second image.