Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Kehua, Yuan, Zhenlong, Mao, Tianlu, Wang, Zhaoqi
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915084046958592
author Chen, Kehua
Yuan, Zhenlong
Mao, Tianlu
Wang, Zhaoqi
author_facet Chen, Kehua
Yuan, Zhenlong
Mao, Tianlu
Wang, Zhaoqi
contents The reconstruction of low-textured areas is a prominent research focus in multi-view stereo (MVS). In recent years, traditional MVS methods have performed exceptionally well in reconstructing low-textured areas by constructing plane models. However, these methods often encounter issues such as crossing object boundaries and limited perception ranges, which undermine the robustness of plane model construction. Building on previous work (APD-MVS), we propose the DPE-MVS method. By introducing dual-level precision edge information, including fine and coarse edges, we enhance the robustness of plane model construction, thereby improving reconstruction accuracy in low-textured areas. Furthermore, by leveraging edge information, we refine the sampling strategy in conventional PatchMatch MVS and propose an adaptive patch size adjustment approach to optimize matching cost calculation in both stochastic and low-textured areas. This additional use of edge information allows for more precise and robust matching. Our method achieves state-of-the-art performance on the ETH3D and Tanks & Temples benchmarks. Notably, our method outperforms all published methods on the ETH3D benchmark.
format Preprint
id arxiv_https___arxiv_org_abs_2412_20328
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization
Chen, Kehua
Yuan, Zhenlong
Mao, Tianlu
Wang, Zhaoqi
Computer Vision and Pattern Recognition
The reconstruction of low-textured areas is a prominent research focus in multi-view stereo (MVS). In recent years, traditional MVS methods have performed exceptionally well in reconstructing low-textured areas by constructing plane models. However, these methods often encounter issues such as crossing object boundaries and limited perception ranges, which undermine the robustness of plane model construction. Building on previous work (APD-MVS), we propose the DPE-MVS method. By introducing dual-level precision edge information, including fine and coarse edges, we enhance the robustness of plane model construction, thereby improving reconstruction accuracy in low-textured areas. Furthermore, by leveraging edge information, we refine the sampling strategy in conventional PatchMatch MVS and propose an adaptive patch size adjustment approach to optimize matching cost calculation in both stochastic and low-textured areas. This additional use of edge information allows for more precise and robust matching. Our method achieves state-of-the-art performance on the ETH3D and Tanks & Temples benchmarks. Notably, our method outperforms all published methods on the ETH3D benchmark.
title Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.20328