PMNI: Pose-free Multi-view Normal Integration for Reflective and Textureless Surface Reconstruction

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Pei, Mingzhi, Cao, Xu, Wang, Xiangyi, Guo, Heng, Ma, Zhanyu
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913790676697088
author Pei, Mingzhi
Cao, Xu
Wang, Xiangyi
Guo, Heng
Ma, Zhanyu
author_facet Pei, Mingzhi
Cao, Xu
Wang, Xiangyi
Guo, Heng
Ma, Zhanyu
contents Reflective and textureless surfaces remain a challenge in multi-view 3D reconstruction. Both camera pose calibration and shape reconstruction often fail due to insufficient or unreliable cross-view visual features. To address these issues, we present PMNI (Pose-free Multi-view Normal Integration), a neural surface reconstruction method that incorporates rich geometric information by leveraging surface normal maps instead of RGB images. By enforcing geometric constraints from surface normals and multi-view shape consistency within a neural signed distance function (SDF) optimization framework, PMNI simultaneously recovers accurate camera poses and high-fidelity surface geometry. Experimental results on synthetic and real-world datasets show that our method achieves state-of-the-art performance in the reconstruction of reflective surfaces, even without reliable initial camera poses.
format Preprint
id arxiv_https___arxiv_org_abs_2504_08410
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PMNI: Pose-free Multi-view Normal Integration for Reflective and Textureless Surface Reconstruction
Pei, Mingzhi
Cao, Xu
Wang, Xiangyi
Guo, Heng
Ma, Zhanyu
Computer Vision and Pattern Recognition
Reflective and textureless surfaces remain a challenge in multi-view 3D reconstruction. Both camera pose calibration and shape reconstruction often fail due to insufficient or unreliable cross-view visual features. To address these issues, we present PMNI (Pose-free Multi-view Normal Integration), a neural surface reconstruction method that incorporates rich geometric information by leveraging surface normal maps instead of RGB images. By enforcing geometric constraints from surface normals and multi-view shape consistency within a neural signed distance function (SDF) optimization framework, PMNI simultaneously recovers accurate camera poses and high-fidelity surface geometry. Experimental results on synthetic and real-world datasets show that our method achieves state-of-the-art performance in the reconstruction of reflective surfaces, even without reliable initial camera poses.
title PMNI: Pose-free Multi-view Normal Integration for Reflective and Textureless Surface Reconstruction
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.08410