FisheyeDistill: Self-Supervised Monocular Depth Estimation with Ordinal Distillation for Fisheye Cameras

TL;DR

This paper introduces FisheyeDistill, a self-supervised monocular depth estimation method for fisheye cameras that uses ordinal distillation from a large teacher model to improve depth accuracy in challenging conditions.

Contribution

It proposes a novel ordinal distillation loss that enhances self-supervised depth estimation for fisheye cameras, especially in difficult environments.

Findings

Improved depth estimation in low-light and homogeneous regions.

Better scene geometry recovery compared to baseline methods.

Effective use of a fisheye camera dataset for indoor evaluation.

Abstract

In this paper, we deal with the problem of monocular depth estimation for fisheye cameras in a self-supervised manner. A known issue of self-supervised depth estimation is that it suffers in low-light/over-exposure conditions and in large homogeneous regions. To tackle this issue, we propose a novel ordinal distillation loss that distills the ordinal information from a large teacher model. Such a teacher model, since having been trained on a large amount of diverse data, can capture the depth ordering information well, but lacks in preserving accurate scene geometry. Combined with self-supervised losses, we show that our model can not only generate reasonable depth maps in challenging environments but also better recover the scene geometry. We further leverage the fisheye cameras of an AR-Glasses device to collect an indoor dataset to facilitate evaluation.