Embodiment: Self-Supervised Depth Estimation Based on Camera Models

TL;DR

This paper introduces a novel self-supervised depth estimation method that incorporates camera physical properties into deep learning models, improving accuracy and reducing reliance on external ground truth data.

Contribution

It embeds camera intrinsic and extrinsic parameters into the neural network to generate depth priors, enhancing unsupervised depth estimation without extra sensors.

Findings

Improved depth estimation accuracy over existing methods.

Reduced need for external ground truth or scale correction.

Easy to implement and compatible with existing unsupervised approaches.

Abstract

Depth estimation is a critical topic for robotics and vision-related tasks. In monocular depth estimation, in comparison with supervised learning that requires expensive ground truth labeling, self-supervised methods possess great potential due to no labeling cost. However, self-supervised learning still has a large gap with supervised learning in 3D reconstruction and depth estimation performance. Meanwhile, scaling is also a major issue for monocular unsupervised depth estimation, which commonly still needs ground truth scale from GPS, LiDAR, or existing maps to correct. In the era of deep learning, existing methods primarily rely on exploring image relationships to train unsupervised neural networks, while the physical properties of the camera itself such as intrinsics and extrinsics are often overlooked. These physical properties are not just mathematical parameters; they are embodiments of the camera's interaction with the physical world. By embedding these physical properties into the deep learning model, we can calculate depth priors for ground regions and regions connected to the ground based on physical principles, providing free supervision signals without the need for additional sensors. This approach is not only easy to implement but also enhances the effects of all unsupervised methods by embedding the camera's physical properties into the model, thereby achieving an embodied understanding of the real world.