GroCo: Ground Constraint for Metric Self-Supervised Monocular Depth

TL;DR

This paper introduces GroCo, a ground constraint method for self-supervised monocular depth estimation that improves scale recovery and model generalization across diverse datasets and camera poses.

Contribution

We propose a novel ground constraint mechanism tailored for self-supervised monocular depth estimation, enhancing scale recovery and cross-dataset generalization.

Findings

Outperforms existing scale recovery methods on KITTI.

Enhances robustness across diverse camera rotations.

Improves zero-shot generalization to unseen datasets.

Abstract

Monocular depth estimation has greatly improved in the recent years but models predicting metric depth still struggle to generalize across diverse camera poses and datasets. While recent supervised methods mitigate this issue by leveraging ground prior information at inference, their adaptability to self-supervised settings is limited due to the additional challenge of scale recovery. Addressing this gap, we propose in this paper a novel constraint on ground areas designed specifically for the self-supervised paradigm. This mechanism not only allows to accurately recover the scale but also ensures coherence between the depth prediction and the ground prior. Experimental results show that our method surpasses existing scale recovery techniques on the KITTI benchmark and significantly enhances model generalization capabilities. This improvement can be observed by its more robust performance across diverse camera rotations and its adaptability in zero-shot conditions with previously unseen driving datasets such as DDAD.