Error Diagnosis of Deep Monocular Depth Estimation Models

Nikhil Thakurdesai, Md A Reza, David J. Crandall

Abstract:

Estimating depth from a monocular image is an
ill-posed problem: when the camera projects a 3D scene onto
a 2D plane, depth information is inherently and permanently
lost. Nevertheless, recent work has shown impressive results in
estimating 3D structure from 2D images using deep learning. In
this paper, we put on an introspective hat and analyze state-of-
the-art monocular depth estimation models in indoor scenes
to understand these models’ limitations and error patterns.
To address errors in depth estimation, we introduce a novel
Depth Error Detection Network (DEDN) that spatially identifies
erroneous depth predictions in the monocular depth estima-
tion models. By experimenting with multiple state-of-the-art
monocular indoor depth estimation models on multiple datasets,
we show that our proposed depth error detection network
can identify a significant number of errors in the predicted
depth maps. Our module is flexible and can be readily plugged
into any monocular depth prediction network to help diagnose
its results. Additionally, we propose a simple yet effective
Depth Error Correction Network (DECN) that iteratively corrects
errors based on our initial error diagnosis.