Accuracy Does Not Guarantee Human-Likeness in Monocular Depth Estimators

TL;DR

This paper investigates the relationship between model accuracy and human-likeness in monocular depth estimation, revealing that higher accuracy does not always equate to more human-like perception, emphasizing the need for human-centric evaluation methods.

Contribution

The study systematically analyzes the correlation between accuracy and human similarity across 69 depth estimators, highlighting the divergence and trade-offs between these aspects.

Findings

Shared estimation biases between humans and DNNs

Trade-off between accuracy and human-likeness in models

Accuracy improvements do not guarantee human-like behavior

Abstract

Monocular depth estimation is a fundamental capability for real-world applications such as autonomous driving and robotics. Although deep neural networks (DNNs) have achieved superhuman accuracy on physical-based benchmarks, a key challenge remains: aligning model representations with human perception, a promising strategy for enhancing model robustness and interpretability. Research in object recognition has revealed a complex trade-off between model accuracy and human-like behavior, raising a question whether a similar divergence exist in depth estimation, particularly for natural outdoor scenes where benchmarks rely on sensor-based ground truth rather than human perceptual estimates. In this study, we systematically investigated the relationship between model accuracy and human similarity across 69 monocular depth estimators using the KITTI dataset. To dissect the structure of error patterns on a factor-by-factor basis, we applied affine fitting to decompose prediction errors into interpretable components. Intriguingly, our results reveal while humans and DNNs share certain estimation biases (positive error correlations), we observed distinct trade-off relationships between model accuracy and human similarity. This finding indicates that improving accuracy does not necessarily lead to more human-like behavior, underscoring the necessity of developing multifaceted, human-centric evaluations beyond traditional accuracy.