CDGS: Confidence-Aware Depth Regularization for 3D Gaussian Splatting
3D Gaussian Splatting (3DGS) has shown significant advantages in novel view synthesis (NVS), particularly in achieving high rendering speeds and high-quality results. However, its geometric accuracy in 3D reconstruction remains limited due to the lack of explicit geometric constraints during optimiz...
Saved in:
| Main Authors: | Q. Zhang, O. Wysocki, S. Urban, B. Jutzi |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2024-12-01
|
| Series: | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| Online Access: | https://isprs-archives.copernicus.org/articles/XLVIII-2-W7-2024/189/2024/isprs-archives-XLVIII-2-W7-2024-189-2024.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
ThermalGS: Dynamic 3D Thermal Reconstruction with Gaussian Splatting
by: Yuxiang Liu, et al.
Published: (2025-01-01) -
Performance Evaluation and Optimization of 3D Gaussian Splatting in Indoor Scene Generation and Rendering
by: Xinjian Fang, et al.
Published: (2025-01-01) -
Arbitrary Optics for Gaussian Splatting Using Space Warping
by: Jakob Nazarenus, et al.
Published: (2024-12-01) -
HoloGaussian Digital Twin: Reconstructing 3D Scenes with Gaussian Splatting for Tabletop Hologram Visualization of Real Environments
by: Tam Le Phuc Do, et al.
Published: (2024-12-01) -
Impact of Camera Settings on 3D Reconstruction Quality: Insights from NeRF and Gaussian Splatting
by: Dimitar Rangelov, et al.
Published: (2024-11-01)