The Third Monocular Depth Estimation Challenge

TL;DR

This paper reports on the third Monocular Depth Estimation Challenge, emphasizing zero-shot generalization to complex scenes, with recent methods leveraging foundational models to significantly improve 3D F-Score performance.

Contribution

It introduces the third edition of the challenge, highlighting the use of foundational models and demonstrating substantial performance improvements in depth estimation.

Findings

19 submissions outperformed the baseline

Use of foundational models like Depth Anything was common

Winners improved 3D F-Score from 17.51% to 23.72%

Abstract

This paper discusses the results of the third edition of the Monocular Depth Estimation Challenge (MDEC). The challenge focuses on zero-shot generalization to the challenging SYNS-Patches dataset, featuring complex scenes in natural and indoor settings. As with the previous edition, methods can use any form of supervision, i.e. supervised or self-supervised. The challenge received a total of 19 submissions outperforming the baseline on the test set: 10 among them submitted a report describing their approach, highlighting a diffused use of foundational models such as Depth Anything at the core of their method. The challenge winners drastically improved 3D F-Score performance, from 17.51% to 23.72%.