Deep Planar Parallax for Monocular Depth Estimation

Recent research has highlighted the utility of Planar Parallax Geometry in monocular depth estimation. However, its potential has yet to be fully realized because networks rely heavily on appearance for depth prediction. Our in-depth analysis reveals that utilizing flow-pretrain can optimize the net...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Liang, Haoqian, Li, Zhichao, Yang, Ya, Wang, Naiyan
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 28.11.2023
Subjects
Datasets
Learning
Parallax
Online AccessGet full text

Cover

More Information
Summary:Recent research has highlighted the utility of Planar Parallax Geometry in monocular depth estimation. However, its potential has yet to be fully realized because networks rely heavily on appearance for depth prediction. Our in-depth analysis reveals that utilizing flow-pretrain can optimize the network's usage of consecutive frame modeling, leading to substantial performance enhancement. Additionally, we propose Planar Position Embedding (PPE) to handle dynamic objects that defy static scene assumptions and to tackle slope variations that are challenging to differentiate. Comprehensive experiments on autonomous driving datasets, namely KITTI and the Waymo Open Dataset (WOD), prove that our Planar Parallax Network (PPNet) significantly surpasses existing learning-based methods in performance.
ISSN:2331-8422