Deep Convolutional Compressed Sensing for LiDAR Depth Completion
This addresses depth completion for LiDAR-based perception systems, offering a highly efficient solution compared to existing methods.
The paper tackles the problem of estimating dense depth maps from sparse LiDAR points using a deep recurrent auto-encoder based on compressed sensing and Alternating Direction Neural Networks, achieving state-of-the-art results with only two layers and 1800 parameters.
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 recurrent auto-encoder for this task. Our architecture internally performs an algorithm for extracting multi-level convolutional sparse codes from the input which are then used to make a prediction. Our results demonstrate that with only two layers and 1800 parameters we are able to out perform all previously published results, including deep networks with orders of magnitude more parameters.