DepthCues: Evaluating Monocular Depth Perception in Large Vision Models

TL;DR

This paper investigates how monocular depth cues emerge in large pre-trained vision models without explicit depth supervision, introduces a new benchmark for evaluation, and demonstrates that fine-tuning can enhance depth perception.

Contribution

The paper introduces the DepthCues benchmark to evaluate depth perception in vision models and analyzes the emergence of human-like depth cues in large models without explicit supervision.

Findings

Depth cues emerge more prominently in larger models.

Fine-tuning on DepthCues improves depth estimation.

The benchmark and code are publicly available.

Abstract

Large-scale pre-trained vision models are becoming increasingly prevalent, offering expressive and generalizable visual representations that benefit various downstream tasks. Recent studies on the emergent properties of these models have revealed their high-level geometric understanding, in particular in the context of depth perception. However, it remains unclear how depth perception arises in these models without explicit depth supervision provided during pre-training. To investigate this, we examine whether the monocular depth cues, similar to those used by the human visual system, emerge in these models. We introduce a new benchmark, DepthCues, designed to evaluate depth cue understanding, and present findings across 20 diverse and representative pre-trained vision models. Our analysis shows that human-like depth cues emerge in more recent larger models. We also explore enhancing depth perception in large vision models by fine-tuning on DepthCues, and find that even without dense depth supervision, this improves depth estimation. To support further research, our benchmark and evaluation code will be made publicly available for studying depth perception in vision models.