Efficient Single-Image Depth Estimation on Mobile Devices, Mobile AI & AIM 2022 Challenge: Report

TL;DR

This paper reports on a challenge to develop efficient, real-time single-image depth estimation models suitable for low-power mobile and IoT devices, demonstrating high performance on Raspberry Pi 4 and Android platforms.

Contribution

It introduces a large-scale RGB-to-depth dataset and presents deep learning solutions capable of real-time depth estimation on mobile hardware.

Findings

Models achieve up to 27 FPS on Raspberry Pi 4.

Depth maps are generated at VGA resolution with high fidelity.

Solutions are compatible with Android and Linux-based mobile devices.

Abstract

Various depth estimation models are now widely used on many mobile and IoT devices for image segmentation, bokeh effect rendering, object tracking and many other mobile tasks. Thus, it is very crucial to have efficient and accurate depth estimation models that can run fast on low-power mobile chipsets. In this Mobile AI challenge, the target was to develop deep learning-based single image depth estimation solutions that can show a real-time performance on IoT platforms and smartphones. For this, the participants used a large-scale RGB-to-depth dataset that was collected with the ZED stereo camera capable to generated depth maps for objects located at up to 50 meters. The runtime of all models was evaluated on the Raspberry Pi 4 platform, where the developed solutions were able to generate VGA resolution depth maps at up to 27 FPS while achieving high fidelity results. All models developed in the challenge are also compatible with any Android or Linux-based mobile devices, their detailed description is provided in this paper.