Towards General Purpose Geometry-Preserving Single-View Depth Estimation

TL;DR

This paper introduces a method for single-view depth estimation that leverages limited geometrically accurate data to achieve state-of-the-art results in scene understanding, with improved 3D reconstruction capabilities.

Contribution

It demonstrates that training on a small subset of geometrically correct depth maps, combined with other datasets, can produce highly accurate and generalizable depth estimation models.

Findings

Models trained with limited geometrically correct data perform comparably to those trained on full datasets.

The proposed method achieves state-of-the-art results on unseen datasets.

Qualitative 3D reconstructions show improved scene geometry accuracy.

Abstract

Single-view depth estimation (SVDE) plays a crucial role in scene understanding for AR applications, 3D modeling, and robotics, providing the geometry of a scene based on a single image. Recent works have shown that a successful solution strongly relies on the diversity and volume of training data. This data can be sourced from stereo movies and photos. However, they do not provide geometrically complete depth maps (as disparities contain unknown shift value). Therefore, existing models trained on this data are not able to recover correct 3D representations. Our work shows that a model trained on this data along with conventional datasets can gain accuracy while predicting correct scene geometry. Surprisingly, only a small portion of geometrically correct depth maps are required to train a model that performs equally to a model trained on the full geometrically correct dataset. After that, we train computationally efficient models on a mixture of datasets using the proposed method. Through quantitative comparison on completely unseen datasets and qualitative comparison of 3D point clouds, we show that our model defines the new state of the art in general-purpose SVDE.