On the Coupling of Depth and Egomotion Networks for Self-Supervised Structure from Motion

TL;DR

This paper proposes a novel tightly-coupled approach for jointly training depth and egomotion networks in self-supervised SfM, improving consistency, generalization, and accuracy across benchmarks.

Contribution

It introduces a new coupling method that leverages interdependence during training and testing, using iterative view synthesis for recursive updates.

Findings

Achieves state-of-the-art accuracy on indoor and outdoor benchmarks.

Promotes consistency between depth and egomotion predictions.

Improves generalization of the models.

Abstract

Structure from motion (SfM) has recently been formulated as a self-supervised learning problem, where neural network models of depth and egomotion are learned jointly through view synthesis. Herein, we address the open problem of how to best couple, or link, the depth and egomotion network components, so that information such as a common scale factor can be shared between the networks. Towards this end, we introduce several notions of coupling, categorize existing approaches, and present a novel tightly-coupled approach that leverages the interdependence of depth and egomotion at training time and at test time. Our approach uses iterative view synthesis to recursively update the egomotion network input, permitting contextual information to be passed between the components. We demonstrate through substantial experiments that our approach promotes consistency between the depth and egomotion predictions at test time, improves generalization, and leads to state-of-the-art accuracy on indoor and outdoor depth and egomotion evaluation benchmarks.