GoMVS: Geometrically Consistent Cost Aggregation for Multi-View Stereo

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Wu, Jiang, Li, Rui, Xu, Haofei, Zhao, Wenxun, Zhu, Yu, Sun, Jinqiu, Zhang, Yanning
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917637564399616
author Wu, Jiang
Li, Rui
Xu, Haofei
Zhao, Wenxun
Zhu, Yu
Sun, Jinqiu
Zhang, Yanning
author_facet Wu, Jiang
Li, Rui
Xu, Haofei
Zhao, Wenxun
Zhu, Yu
Sun, Jinqiu
Zhang, Yanning
contents Matching cost aggregation plays a fundamental role in learning-based multi-view stereo networks. However, directly aggregating adjacent costs can lead to suboptimal results due to local geometric inconsistency. Related methods either seek selective aggregation or improve aggregated depth in the 2D space, both are unable to handle geometric inconsistency in the cost volume effectively. In this paper, we propose GoMVS to aggregate geometrically consistent costs, yielding better utilization of adjacent geometries. More specifically, we correspond and propagate adjacent costs to the reference pixel by leveraging the local geometric smoothness in conjunction with surface normals. We achieve this by the geometric consistent propagation (GCP) module. It computes the correspondence from the adjacent depth hypothesis space to the reference depth space using surface normals, then uses the correspondence to propagate adjacent costs to the reference geometry, followed by a convolution for aggregation. Our method achieves new state-of-the-art performance on DTU, Tanks & Temple, and ETH3D datasets. Notably, our method ranks 1st on the Tanks & Temple Advanced benchmark.
format Preprint
id arxiv_https___arxiv_org_abs_2404_07992
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle GoMVS: Geometrically Consistent Cost Aggregation for Multi-View Stereo
Wu, Jiang
Li, Rui
Xu, Haofei
Zhao, Wenxun
Zhu, Yu
Sun, Jinqiu
Zhang, Yanning
Computer Vision and Pattern Recognition
Matching cost aggregation plays a fundamental role in learning-based multi-view stereo networks. However, directly aggregating adjacent costs can lead to suboptimal results due to local geometric inconsistency. Related methods either seek selective aggregation or improve aggregated depth in the 2D space, both are unable to handle geometric inconsistency in the cost volume effectively. In this paper, we propose GoMVS to aggregate geometrically consistent costs, yielding better utilization of adjacent geometries. More specifically, we correspond and propagate adjacent costs to the reference pixel by leveraging the local geometric smoothness in conjunction with surface normals. We achieve this by the geometric consistent propagation (GCP) module. It computes the correspondence from the adjacent depth hypothesis space to the reference depth space using surface normals, then uses the correspondence to propagate adjacent costs to the reference geometry, followed by a convolution for aggregation. Our method achieves new state-of-the-art performance on DTU, Tanks & Temple, and ETH3D datasets. Notably, our method ranks 1st on the Tanks & Temple Advanced benchmark.
title GoMVS: Geometrically Consistent Cost Aggregation for Multi-View Stereo
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2404.07992