NeuralSampler: Euclidean Point Cloud Auto-Encoder and SamplerA

Jan 22, 2020

We propose an auto-encoder architecture that can both encode and decode clouds of arbitrary size and demonstrate its effectiveness at upsampling sparse point clouds. Interestingly, we can do so using less than half as many parameters as state-of-the-art architectures while still delivering better performance.

You can download the full publication here.