arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2406.05774cs.CV
收藏

VCR-GauS:面向高斯表面重建的视角一致深度-法向正则化器

VCR-GauS: View Consistent Depth-Normal Regularizer for Gaussian Surface Reconstruction

School of Computing, National University of Singapore(新加坡国立大学计算机学院);Princeton University(普林斯顿大学)

Hanlin Chen, Fangyin Wei, Chen Li, Tianxin Huang, Yunsong Wang, Gim Hee Lee

AI总结:

针对3D高斯表面重建中法向正则化参数优化不充分、多视角法向不一致的问题,提出深度-法向正则化器、多视角置信度项及高斯致密分裂策略,在更快训练速度和100+ FPS渲染下实现更优重建质量与有竞争力的外观质量。

摘要:

尽管3D Gaussian Splatting(三维高斯泼溅)凭借其真实且高效的新视角合成效果已被广泛研究,但从基于点的表示中提取高质量表面仍具有挑战性。已有工作通过引入现成法向估计器的几何先验来改进表面,但存在两个主要局限:1)监督由3D高斯渲染出的法向可有效更新旋转参数,但对其他几何参数的优化效果较弱;2)多视角下预测法向图的不一致性可能导致严重的重建伪影。本文提出一种深度-法向正则化器,将法向与其他几何参数直接耦合,实现了法向正则化对几何参数的全面更新。我们进一步提出了一个置信度项,以缓解多视角下法向预测的不一致性。此外,我们还引入了一种致密化与分裂策略,对3D高斯的大小和分布进行正则化,以实现更精准的表面建模。与基于高斯的基线方法相比,实验表明我们的方法获得了更优的重建质量,同时保持了有竞争力的外观质量,且训练速度更快,渲染帧率可达100+ FPS。

英文摘要:

Although 3D Gaussian Splatting has been widely studied because of its realistic and efficient novel-view synthesis, it is still challenging to extract a high-quality surface from the point-based representation. Previous works improve the surface by incorporating geometric priors from the off-the-shelf normal estimator. However, there are two main limitations: 1) Supervising normals rendered from 3D Gaussians effectively updates the rotation parameter but is less effective for other geometric parameters; 2) The inconsistency of predicted normal maps across multiple views may lead to severe reconstruction artifacts. In this paper, we propose a Depth-Normal regularizer that directly couples normal with other geometric parameters, leading to full updates of the geometric parameters from normal regularization. We further propose a confidence term to mitigate inconsistencies of normal predictions across multiple views. Moreover, we also introduce a densification and splitting strategy to regularize the size and distribution of 3D Gaussians for more accurate surface modeling. Compared with Gaussian-based baselines, experiments show that our approach obtains better reconstruction quality and maintains competitive appearance quality at faster training speed and 100+ FPS rendering.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑