Report
VCR-GauS: View Consistent Depth-Normal Regularizer for Gaussian Surface Reconstruction
| العنوان: | VCR-GauS: View Consistent Depth-Normal Regularizer for Gaussian Surface Reconstruction |
|---|---|
| المؤلفون: | Chen, Hanlin, Wei, Fangyin, Li, Chen, Huang, Tianxin, Wang, Yunsong, Lee, Gim Hee |
| سنة النشر: | 2024 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Computer Vision and Pattern Recognition |
| الوصف: | 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. Comment: Project page: https://hlinchen.github.io/projects/VCR-GauS/ |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2406.05774 |
| رقم الانضمام: | edsarx.2406.05774 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |