Monocular Depth Estimation via Listwise Ranking using the Plackett-Luce Model

TL;DR

This paper introduces a listwise ranking approach using the Plackett-Luce model for monocular depth estimation, outperforming existing methods by leveraging ranking data and neural networks.

Contribution

It proposes a novel listwise ranking method based on the Plackett-Luce model for depth estimation, improving accuracy and efficiency over pairwise approaches.

Findings

Outperforms existing ranking and regression methods on benchmark datasets.

Effectively recovers metric depth from ranking-only training data.

Demonstrates robustness in zero-shot evaluation settings.

Abstract

In many real-world applications, the relative depth of objects in an image is crucial for scene understanding. Recent approaches mainly tackle the problem of depth prediction in monocular images by treating the problem as a regression task. Yet, being interested in an order relation in the first place, ranking methods suggest themselves as a natural alternative to regression, and indeed, ranking approaches leveraging pairwise comparisons as training information ("object A is closer to the camera than B") have shown promising performance on this problem. In this paper, we elaborate on the use of so-called listwise ranking as a generalization of the pairwise approach. Our method is based on the Plackett-Luce (PL) model, a probability distribution on rankings, which we combine with a state-of-the-art neural network architecture and a simple sampling strategy to reduce training complexity. Moreover, taking advantage of the representation of PL as a random utility model, the proposed predictor offers a natural way to recover (shift-invariant) metric depth information from ranking-only data provided at training time. An empirical evaluation on several benchmark datasets in a "zero-shot" setting demonstrates the effectiveness of our approach compared to existing ranking and regression methods.