SC-DepthV3: Robust Self-supervised Monocular Depth Estimation for Dynamic Scenes

Libo Sun*, Jia-Wang Bian* , Huangying Zhan , Wei Yin , Ian Reid, Chunhua Shen
* denotes equal contribution and joint first author

Arxiv Bibtex Code

Abstract & Method

Self-supervised monocular depth estimation has shown impressive results in static scenes. It relies on the multi-view consistency assumption for training networks, however, that is violated in dynamic object regions and occlusions. Consequently, existing methods show poor accuracy in dynamic scenes, and the estimated depth map is blurred at object boundaries because they are usually occluded in other training views. In this paper, we propose SC-DepthV3 for addressing the challenges. Specifically, we introduce an external pretrained monocular depth estimation model for generating single-image depth prior, namely pseudo-depth, based on which we propose novel losses to boost self-supervised training. As a result, our model can predict sharp and accurate depth maps, even when training from monocular videos of highly-dynamic scenes. We demonstrate the significantly superior performance of our method over previous methods on six challenging datasets, and we provide detailed ablation studies for the proposed terms.

Evaluation of Depth Accuracy in Dynamic Scenes

More Qulatative Comparison

BibTeX

@article{sc_depthv3, 
title={SC-DepthV3: Robust Self-supervised Monocular Depth Estimation for Dynamic Scenes}, 
author={Sun, Libo and Bian, Jia-Wang and Zhan, Huangying and Yin, Wei and Reid, Ian and Shen, Chunhua}, 
journal= {IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)}, 
year={2023} 
}