Prior-Driven Enhancements in 3D Gaussian Splatting: Normals and Depths Regularization
3D Gaussian Splatting (3DGS) is a state-of-the-art technique for 3D scene rendering, offering high efficiency and excellent visual quality. However, because 3DGS relies on an initial sparse point set from Structure-from-Motion (SfM) and view-dependent properties, it can suffer from geometric inaccur...
Saved in:
| Main Authors: | G. Lee, S. Hong, J. Suh |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2025-07-01
|
| Series: | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| Online Access: | https://isprs-archives.copernicus.org/articles/XLVIII-G-2025/891/2025/isprs-archives-XLVIII-G-2025-891-2025.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Depth-Supervised and Curvature-Optimized 3D Gaussian Splatting for Scene Reconstruction
by: Antong Li, et al.
Published: (2025-01-01) -
Dual-Dimensional Gaussian Splatting Integrating 2D and 3D Gaussians for Surface Reconstruction
by: Jichan Park, et al.
Published: (2025-06-01) -
BrushGaussian: Brushstroke-Based Stylization for 3D Gaussian Splatting
by: Zhi-Zheng Xiang, et al.
Published: (2025-06-01) -
UDGS-SLAM: UniDepth Assisted Gaussian Splatting for Monocular SLAM
by: Mostafa Mansour, et al.
Published: (2025-07-01) -
3D Gaussian Splatting Methods for Real-World Scenarios
by: I. Petrovska, et al.
Published: (2025-07-01)