DnD: Dense Depth Estimation in Crowded Dynamic Indoor Scenes

TL;DR

This paper introduces a novel monocular depth estimation method for crowded indoor scenes that predicts dense depth maps without requiring dense ground truth, leveraging sparse reconstructions and handling dynamic objects.

Contribution

It presents a new training framework for depth estimation in crowded scenes without needing dense depth labels, using RGB images and sparse reconstructions.

Findings

Outperforms recent depth estimation methods on NAVERLABS dataset

Handles dynamic, non-rigid moving objects without explicit tracking

Provides consistent depth predictions in complex indoor environments

Abstract

We present a novel approach for estimating depth from a monocular camera as it moves through complex and crowded indoor environments, e.g., a department store or a metro station. Our approach predicts absolute scale depth maps over the entire scene consisting of a static background and multiple moving people, by training on dynamic scenes. Since it is difficult to collect dense depth maps from crowded indoor environments, we design our training framework without requiring depths produced from depth sensing devices. Our network leverages RGB images and sparse depth maps generated from traditional 3D reconstruction methods to estimate dense depth maps. We use two constraints to handle depth for non-rigidly moving people without tracking their motion explicitly. We demonstrate that our approach offers consistent improvements over recent depth estimation methods on the NAVERLABS dataset, which includes complex and crowded scenes.