DVMN: Dense Validity Mask Network for Depth Completion

TL;DR

DVMN is a novel neural network for depth completion that effectively utilizes sparse LiDAR data by introducing a new layer with spatially variant dilation and a sparsity invariant residual block, achieving state-of-the-art results.

Contribution

The paper presents a new guided convolutional neural network with a novel dilation layer and residual block for improved depth completion from sparse LiDAR data.

Findings

Achieves state-of-the-art results on KITTI benchmark.

First to use sparsity invariant convolution for depth completion.

Outperforms previous methods in accuracy and robustness.

Abstract

LiDAR depth maps provide environmental guidance in a variety of applications. However, such depth maps are typically sparse and insufficient for complex tasks such as autonomous navigation. State of the art methods use image guided neural networks for dense depth completion. We develop a guided convolutional neural network focusing on gathering dense and valid information from sparse depth maps. To this end, we introduce a novel layer with spatially variant and content-depended dilation to include additional data from sparse input. Furthermore, we propose a sparsity invariant residual bottleneck block. We evaluate our Dense Validity Mask Network (DVMN) on the KITTI depth completion benchmark and achieve state of the art results. At the time of submission, our network is the leading method using sparsity invariant convolution.