Towards Depth Foundation Model: Recent Trends in Vision-Based Depth Estimation

TL;DR

This paper surveys recent progress in vision-based depth estimation, emphasizing the development of large-scale models with strong generalization capabilities to overcome traditional limitations.

Contribution

It provides a comprehensive overview of deep learning architectures, datasets, and training strategies for creating robust depth foundation models in computer vision.

Findings

Deep learning architectures have evolved to improve depth estimation accuracy.

Large-scale datasets are crucial for training models with zero-shot generalization.

Scaling laws and foundation models show promise for robust depth estimation.

Abstract

Depth estimation is a fundamental task in 3D computer vision, crucial for applications such as 3D reconstruction, free-viewpoint rendering, robotics, autonomous driving, and AR/VR technologies. Traditional methods relying on hardware sensors like LiDAR are often limited by high costs, low resolution, and environmental sensitivity, limiting their applicability in real-world scenarios. Recent advances in vision-based methods offer a promising alternative, yet they face challenges in generalization and stability due to either the low-capacity model architectures or the reliance on domain-specific and small-scale datasets. The emergence of scaling laws and foundation models in other domains has inspired the development of "depth foundation models": deep neural networks trained on large datasets with strong zero-shot generalization capabilities. This paper surveys the evolution of deep learning architectures and paradigms for depth estimation across the monocular, stereo, multi-view, and monocular video settings. We explore the potential of these models to address existing challenges and provide a comprehensive overview of large-scale datasets that can facilitate their development. By identifying key architectures and training strategies, we aim to highlight the path towards robust depth foundation models, offering insights into their future research and applications.