Uncertainty and Self-Supervision in Single-View Depth

TL;DR

This paper introduces a self-supervised, uncertainty-aware deep learning approach for single-view depth estimation, particularly in medical endoscopy, leveraging illumination cues and domain adaptation to improve depth predictions without requiring annotated data.

Contribution

It presents a novel uncertainty-aware teacher-student architecture trained in a self-supervised manner, utilizing illumination as a supervisory signal for depth estimation in unannotated images.

Findings

Effective depth estimation in endoscopy without annotated data

Improved domain transfer from synthetic to real images

Uncertainty quantification enhances prediction reliability

Abstract

Single-view depth estimation refers to the ability to derive three-dimensional information per pixel from a single two-dimensional image. Single-view depth estimation is an ill-posed problem because there are multiple depth solutions that explain 3D geometry from a single view. While deep neural networks have been shown to be effective at capturing depth from a single view, the majority of current methodologies are deterministic in nature. Accounting for uncertainty in the predictions can avoid disastrous consequences when applied to fields such as autonomous driving or medical robotics. We have addressed this problem by quantifying the uncertainty of supervised single-view depth for Bayesian deep neural networks. There are scenarios, especially in medicine in the case of endoscopic images, where such annotated data is not available. To alleviate the lack of data, we present a method that improves the transition from synthetic to real domain methods. We introduce an uncertainty-aware teacher-student architecture that is trained in a self-supervised manner, taking into account the teacher uncertainty. Given the vast amount of unannotated data and the challenges associated with capturing annotated depth in medical minimally invasive procedures, we advocate a fully self-supervised approach that only requires RGB images and the geometric and photometric calibration of the endoscope. In endoscopic imaging, the camera and light sources are co-located at a small distance from the target surfaces. This setup indicates that brighter areas of the image are nearer to the camera, while darker areas are further away. Building on this observation, we exploit the fact that for any given albedo and surface orientation, pixel brightness is inversely proportional to the square of the distance. We propose the use of illumination as a strong single-view self-supervisory signal for deep neural networks.