Saved in:
Bibliographic Details
Main Authors: Li, Pengzhi, Ding, Yikang, Wang, Haohan, Tang, Chengshuai, Li, Zhiheng
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2404.00373
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916186324729856
author Li, Pengzhi
Ding, Yikang
Wang, Haohan
Tang, Chengshuai
Li, Zhiheng
author_facet Li, Pengzhi
Ding, Yikang
Wang, Haohan
Tang, Chengshuai
Li, Zhiheng
contents This paper presents a novel monocular depth estimation method, named ECFNet, for estimating high-quality monocular depth with clear edges and valid overall structure from a single RGB image. We make a thorough inquiry about the key factor that affects the edge depth estimation of the MDE networks, and come to a ratiocination that the edge information itself plays a critical role in predicting depth details. Driven by this analysis, we propose to explicitly employ the image edges as input for ECFNet and fuse the initial depths from different sources to produce the final depth. Specifically, ECFNet first uses a hybrid edge detection strategy to get the edge map and edge-highlighted image from the input image, and then leverages a pre-trained MDE network to infer the initial depths of the aforementioned three images. After that, ECFNet utilizes a layered fusion module (LFM) to fuse the initial depth, which will be further updated by a depth consistency module (DCM) to form the final estimation. Extensive experimental results on public datasets and ablation studies indicate that our method achieves state-of-the-art performance. Project page: https://zrealli.github.io/edgedepth.
format Preprint
id arxiv_https___arxiv_org_abs_2404_00373
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle The Devil is in the Edges: Monocular Depth Estimation with Edge-aware Consistency Fusion
Li, Pengzhi
Ding, Yikang
Wang, Haohan
Tang, Chengshuai
Li, Zhiheng
Computer Vision and Pattern Recognition
This paper presents a novel monocular depth estimation method, named ECFNet, for estimating high-quality monocular depth with clear edges and valid overall structure from a single RGB image. We make a thorough inquiry about the key factor that affects the edge depth estimation of the MDE networks, and come to a ratiocination that the edge information itself plays a critical role in predicting depth details. Driven by this analysis, we propose to explicitly employ the image edges as input for ECFNet and fuse the initial depths from different sources to produce the final depth. Specifically, ECFNet first uses a hybrid edge detection strategy to get the edge map and edge-highlighted image from the input image, and then leverages a pre-trained MDE network to infer the initial depths of the aforementioned three images. After that, ECFNet utilizes a layered fusion module (LFM) to fuse the initial depth, which will be further updated by a depth consistency module (DCM) to form the final estimation. Extensive experimental results on public datasets and ablation studies indicate that our method achieves state-of-the-art performance. Project page: https://zrealli.github.io/edgedepth.
title The Devil is in the Edges: Monocular Depth Estimation with Edge-aware Consistency Fusion
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2404.00373