Unsupervised Monocular Depth Prediction for Indoor Continuous Video Streams

TL;DR

This paper advances unsupervised monocular depth prediction for indoor video streams by evaluating existing methods, identifying challenges due to indoor camera movement, and proposing new loss functions and ensemble techniques to improve accuracy.

Contribution

It introduces a novel reconstruction loss for pose estimation and an ensemble flipping strategy with median filtering tailored for indoor environments.

Findings

Outperforms previous state-of-the-art methods on indoor datasets

Improves disparity map accuracy through new loss function

Enhances pose estimation with ensemble and filtering techniques

Abstract

This paper studies unsupervised monocular depth prediction problem. Most of existing unsupervised depth prediction algorithms are developed for outdoor scenarios, while the depth prediction work in the indoor environment is still very scarce to our knowledge. Therefore, this work focuses on narrowing the gap by firstly evaluating existing approaches in the indoor environments and then improving the state-of-the-art design of architecture. Unlike typical outdoor training dataset, such as KITTI with motion constraints, data for indoor environment contains more arbitrary camera movement and short baseline between two consecutive images, which deteriorates the network training for the pose estimation. To address this issue, we propose two methods: Firstly, we propose a novel reconstruction loss function to constraint pose estimation, resulting in accuracy improvement of the predicted disparity map; secondly, we use an ensemble learning with a flipping strategy along with a median filter, directly taking operation on the output disparity map. We evaluate our approaches on the TUM RGB-D and self-collected datasets. The results have shown that both approaches outperform the previous state-of-the-art unsupervised learning approaches.