The Monocular Depth Estimation Challenge

TL;DR

The Monocular Depth Estimation Challenge at WACV2023 assessed progress in self-supervised monocular depth estimation, highlighting advancements over baselines and identifying persistent challenges in pointcloud reconstruction and boundary accuracy.

Contribution

This paper introduces the first Monocular Depth Estimation Challenge, providing a benchmark for evaluating state-of-the-art algorithms and fostering progress in the field.

Findings

All participants outperformed baselines in traditional metrics.

Pointcloud reconstruction remains challenging with current methods.

Predictions often have boundary artifacts and relative positioning errors.

Abstract

This paper summarizes the results of the first Monocular Depth Estimation Challenge (MDEC) organized at WACV2023. This challenge evaluated the progress of self-supervised monocular depth estimation on the challenging SYNS-Patches dataset. The challenge was organized on CodaLab and received submissions from 4 valid teams. Participants were provided a devkit containing updated reference implementations for 16 State-of-the-Art algorithms and 4 novel techniques. The threshold for acceptance for novel techniques was to outperform every one of the 16 SotA baselines. All participants outperformed the baseline in traditional metrics such as MAE or AbsRel. However, pointcloud reconstruction metrics were challenging to improve upon. We found predictions were characterized by interpolation artefacts at object boundaries and errors in relative object positioning. We hope this challenge is a valuable contribution to the community and encourage authors to participate in future editions.