DiPE: Deeper into Photometric Errors for Unsupervised Learning of Depth and Ego-motion from Monocular Videos

TL;DR

This paper introduces a novel outlier masking technique and a multi-scale scheme to improve unsupervised depth and ego-motion learning from monocular videos, especially in challenging scenarios like moving objects, achieving state-of-the-art results.

Contribution

It presents a statistical outlier masking method and a multi-scale approach that enhance depth and ego-motion estimation accuracy in unsupervised learning from monocular videos.

Findings

Improved depth estimation for moving objects in opposite directions to the camera.

Enhanced robustness of ego-motion estimation in dynamic scenes.

Achieved state-of-the-art performance on KITTI dataset.

Abstract

Unsupervised learning of depth and ego-motion from unlabelled monocular videos has recently drawn great attention, which avoids the use of expensive ground truth in the supervised one. It achieves this by using the photometric errors between the target view and the synthesized views from its adjacent source views as the loss. Despite significant progress, the learning still suffers from occlusion and scene dynamics. This paper shows that carefully manipulating photometric errors can tackle these difficulties better. The primary improvement is achieved by a statistical technique that can mask out the invisible or nonstationary pixels in the photometric error map and thus prevents misleading the networks. With this outlier masking approach, the depth of objects moving in the opposite direction to the camera can be estimated more accurately. To the best of our knowledge, such scenarios have not been seriously considered in the previous works, even though they pose a higher risk in applications like autonomous driving. We also propose an efficient weighted multi-scale scheme to reduce the artifacts in the predicted depth maps. Extensive experiments on the KITTI dataset show the effectiveness of the proposed approaches. The overall system achieves state-of-theart performance on both depth and ego-motion estimation.