Sparse-to-Continuous: Enhancing Monocular Depth Estimation using Occupancy Maps

TL;DR

This paper introduces Sparse-to-Continuous, a densification method for LiDAR-based depth maps using occupancy maps, significantly improving monocular depth estimation without altering neural network architectures.

Contribution

The paper presents a novel densification approach using occupancy maps to enhance depth maps, improving supervised monocular depth estimation for outdoor scenes.

Findings

Significant improvement in depth prediction accuracy on KITTI dataset

Effective densification of sparse LiDAR data without extra training data

Enhanced depth map quality for outdoor scene understanding

Abstract

This paper addresses the problem of single image depth estimation (SIDE), focusing on improving the quality of deep neural network predictions. In a supervised learning scenario, the quality of predictions is intrinsically related to the training labels, which guide the optimization process. For indoor scenes, structured-light-based depth sensors (e.g. Kinect) are able to provide dense, albeit short-range, depth maps. On the other hand, for outdoor scenes, LiDARs are considered the standard sensor, which comparatively provides much sparser measurements, especially in areas further away. Rather than modifying the neural network architecture to deal with sparse depth maps, this article introduces a novel densification method for depth maps, using the Hilbert Maps framework. A continuous occupancy map is produced based on 3D points from LiDAR scans, and the resulting reconstructed surface is projected into a 2D depth map with arbitrary resolution. Experiments conducted with various subsets of the KITTI dataset show a significant improvement produced by the proposed Sparse-to-Continuous technique, without the introduction of extra information into the training stage.