PMNI: Pose-Free Multi-View Normal Integration for Reflective and Textureless Surface Reconstruction
Abstract
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.
Cite
Text
Pei et al. "PMNI: Pose-Free Multi-View Normal Integration for Reflective and Textureless Surface Reconstruction." Conference on Computer Vision and Pattern Recognition, 2025. doi:10.1109/CVPR52734.2025.02499Markdown
[Pei et al. "PMNI: Pose-Free Multi-View Normal Integration for Reflective and Textureless Surface Reconstruction." Conference on Computer Vision and Pattern Recognition, 2025.](https://mlanthology.org/cvpr/2025/pei2025cvpr-pmni/) doi:10.1109/CVPR52734.2025.02499BibTeX
@inproceedings{pei2025cvpr-pmni,
title = {{PMNI: Pose-Free Multi-View Normal Integration for Reflective and Textureless Surface Reconstruction}},
author = {Pei, Mingzhi and Cao, Xu and Wang, Xiangyi and Guo, Heng and Ma, Zhanyu},
booktitle = {Conference on Computer Vision and Pattern Recognition},
year = {2025},
pages = {26834-26843},
doi = {10.1109/CVPR52734.2025.02499},
url = {https://mlanthology.org/cvpr/2025/pei2025cvpr-pmni/}
}