GVGS: Gaussian Visibility-Aware Multi-View Geometry for Accurate Surface Reconstruction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Su, Mai, Yu, Qihan, Wang, Zhongtao, Li, Yilong, Pan, Chengwei, Chen, Yisong, Wang, Guoping, Zhu, Fei
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908932350410752
author Su, Mai
Yu, Qihan
Wang, Zhongtao
Li, Yilong
Pan, Chengwei
Chen, Yisong
Wang, Guoping
Zhu, Fei
author_facet Su, Mai
Yu, Qihan
Wang, Zhongtao
Li, Yilong
Pan, Chengwei
Chen, Yisong
Wang, Guoping
Zhu, Fei
contents 3D Gaussian Splatting (3DGS) enables efficient rendering, yet accurate surface reconstruction remains challenging due to unreliable geometric supervision. Existing approaches predominantly rely on depth-based reprojection to infer visibility and enforce multi-view consistency, leading to a fundamental circular dependency: visibility estimation requires accurate depth, while depth supervision itself is conditioned on visibility. In this work, we revisit multi-view geometric supervision from the perspective of visibility modeling. Instead of inferring visibility from pixel-wise depth consistency, we explicitly model visibility at the level of Gaussian primitives. We introduce a Gaussian visibility-aware multi-view geometric consistency (GVMV) formulation, which aggregates cross-view visibility of shared Gaussians to construct reliable supervision over co-visible regions. To further incorporate monocular priors, we propose a progressive quadtree-calibrated depth alignment (QDC) strategy that performs block-wise affine calibration under visibility-aware guidance, effectively mitigating scale ambiguity while preserving local geometric structures. Extensive experiments on DTU and Tanks and Temples demonstrate that our method consistently improves reconstruction accuracy over prior Gaussian-based approaches. Our code is fully open-sourced and available at an anonymous repository: https://github.com/GVGScode/GVGS.
format Preprint
id arxiv_https___arxiv_org_abs_2601_20331
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle GVGS: Gaussian Visibility-Aware Multi-View Geometry for Accurate Surface Reconstruction
Su, Mai
Yu, Qihan
Wang, Zhongtao
Li, Yilong
Pan, Chengwei
Chen, Yisong
Wang, Guoping
Zhu, Fei
Computer Vision and Pattern Recognition
3D Gaussian Splatting (3DGS) enables efficient rendering, yet accurate surface reconstruction remains challenging due to unreliable geometric supervision. Existing approaches predominantly rely on depth-based reprojection to infer visibility and enforce multi-view consistency, leading to a fundamental circular dependency: visibility estimation requires accurate depth, while depth supervision itself is conditioned on visibility. In this work, we revisit multi-view geometric supervision from the perspective of visibility modeling. Instead of inferring visibility from pixel-wise depth consistency, we explicitly model visibility at the level of Gaussian primitives. We introduce a Gaussian visibility-aware multi-view geometric consistency (GVMV) formulation, which aggregates cross-view visibility of shared Gaussians to construct reliable supervision over co-visible regions. To further incorporate monocular priors, we propose a progressive quadtree-calibrated depth alignment (QDC) strategy that performs block-wise affine calibration under visibility-aware guidance, effectively mitigating scale ambiguity while preserving local geometric structures. Extensive experiments on DTU and Tanks and Temples demonstrate that our method consistently improves reconstruction accuracy over prior Gaussian-based approaches. Our code is fully open-sourced and available at an anonymous repository: https://github.com/GVGScode/GVGS.
title GVGS: Gaussian Visibility-Aware Multi-View Geometry for Accurate Surface Reconstruction
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.20331