Deep Convolutional Compressed Sensing for LiDAR Depth Completion

In this paper we consider the problem of estimating a dense depth map from a set of sparse LiDAR points. We use techniques from compressed sensing and the recently developed Alternating Direction Neural Networks (ADNNs) to create a deep network which performs multi-layer convolutional compressed sensing. Our architecture internally performs the optimization for extracting convolutional sparse codes from the input which are then used to make a prediction. Our results demonstrate that with only three layers and 1800 parameters we achieve performance which is competitive with the state of the art, including deep networks with orders of magnitude more parameters and layers.