Multi-View Stereo Using Perspective-Aware Features and Metadata to Improve Cost Volume

Feature matching is pivotal when using multi-view stereo (MVS) to reconstruct dense 3D models from calibrated images. This paper proposes PAC-MVSNet, which integrates perspective-aware convolution (PAC) and metadata-enhanced cost volumes to address the challenges in reflective and texture-less regio...

Descripción completa

Detalles Bibliográficos

Autores principales:	Zongcheng Zuo, Yuanxiang Li, Yu Zhou, Fan Mo
Formato:	Artigo
Lenguaje:	Inglês
Publicado:	MDPI AG 2025-04-01
Colección:	Sensors
Materias:	3D reconstruction drone remote sensing multi-view stereo feature matching deep learning MVSNet
Acceso en línea:	https://www.mdpi.com/1424-8220/25/7/2233
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!