Adversarial point set registration
This addresses the problem of aligning point clouds in computer vision and robotics, offering a novel method that is incremental in its adaptation of adversarial techniques.
The paper tackles point set registration without relying on correspondences by using a one-shot adversarial learning approach, achieving competitive performance on challenging benchmarks compared to existing baselines.
We present a novel approach to point set registration which is based on one-shot adversarial learning. The idea of the algorithm is inspired by recent successes of generative adversarial networks. Treating the point clouds as three-dimensional probability distributions, we develop a one-shot adversarial optimization procedure, in which we train a critic neural network to distinguish between source and target point sets, while simultaneously learning the parameters of the transformation to trick the critic into confusing the points. In contrast to most existing algorithms for point set registration, ours does not rely on any correspondences between the point clouds. We demonstrate the performance of the algorithm on several challenging benchmarks and compare it to the existing baselines.