Unsupervised Monocular Depth Perception: Focusing on Moving Objects

TL;DR

This paper introduces an outlier masking technique and a multi-scale scheme to improve unsupervised monocular depth estimation, especially for moving objects, demonstrating significant improvements on KITTI and Cityscapes datasets.

Contribution

It proposes novel outlier masking and multi-scale methods to better handle occlusion and scene dynamics in unsupervised depth learning from monocular videos.

Findings

Enhanced depth accuracy for moving objects in unsupervised learning

Effective reduction of artifacts in depth maps

Improved depth and ego-motion estimation results

Abstract

As a flexible passive 3D sensing means, unsupervised learning of depth from monocular videos is becoming an important research topic. It utilizes the photometric errors between the target view and the synthesized views from its adjacent source views as the loss instead of the difference from the ground truth. Occlusion and scene dynamics in real-world scenes still adversely affect the learning, despite significant progress made recently. In this paper, we show that deliberately manipulating photometric errors can efficiently deal with these difficulties better. We first propose an outlier masking technique that considers the occluded or dynamic pixels as statistical outliers in the photometric error map. With the outlier masking, the network learns the depth of objects that move in the opposite direction to the camera more accurately. To the best of our knowledge, such cases have not been seriously considered in the previous works, even though they pose a high 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 and additional experiments on the Cityscapes dataset have verified the proposed approach's effectiveness on depth or ego-motion estimation. Furthermore, for the first time, we evaluate the predicted depth on the regions of dynamic objects and static background separately for both supervised and unsupervised methods. The evaluation further verifies the effectiveness of our proposed technical approach and provides some interesting observations that might inspire future research in this direction.