Error Diagnosis of Deep Monocular Depth Estimation Models
This work addresses error diagnosis for monocular depth estimation models, which is an incremental improvement for applications in robotics and augmented reality.
The paper tackles the problem of diagnosing and correcting errors in deep monocular depth estimation models for indoor scenes by introducing a Depth Error Detection Network (DEDN) that identifies erroneous predictions and a Depth Error Correction Network (DECN) that iteratively corrects them, showing that DEDN can identify a significant number of errors.
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 estimation 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.