Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.02493 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914097691361280 |
|---|---|
| author | Wang, Jianchao Zhou, Peng Li, Cen Quan, Rong Qin, Jie |
| author_facet | Wang, Jianchao Zhou, Peng Li, Cen Quan, Rong Qin, Jie |
| contents | 3D Gaussian Splatting (3DGS) is a powerful and computationally efficient representation for 3D reconstruction. Despite its strengths, 3DGS often produces floating artifacts, which are erroneous structures detached from the actual geometry and significantly degrade visual fidelity. The underlying mechanisms causing these artifacts, particularly in low-quality initialization scenarios, have not been fully explored. In this paper, we investigate the origins of floating artifacts from a frequency-domain perspective and identify under-optimized Gaussians as the primary source. Based on our analysis, we propose \textit{Eliminating-Floating-Artifacts} Gaussian Splatting (EFA-GS), which selectively expands under-optimized Gaussians to prioritize accurate low-frequency learning. Additionally, we introduce complementary depth-based and scale-based strategies to dynamically refine Gaussian expansion, effectively mitigating detail erosion. Extensive experiments on both synthetic and real-world datasets demonstrate that EFA-GS substantially reduces floating artifacts while preserving high-frequency details, achieving an improvement of 1.68 dB in PSNR over baseline method on our RWLQ dataset. Furthermore, we validate the effectiveness of our approach in downstream 3D editing tasks. Project Website: https://jcwang-gh.github.io/EFA-GS |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_02493 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Low-Frequency First: Eliminating Floating Artifacts in 3D Gaussian Splatting Wang, Jianchao Zhou, Peng Li, Cen Quan, Rong Qin, Jie Computer Vision and Pattern Recognition 3D Gaussian Splatting (3DGS) is a powerful and computationally efficient representation for 3D reconstruction. Despite its strengths, 3DGS often produces floating artifacts, which are erroneous structures detached from the actual geometry and significantly degrade visual fidelity. The underlying mechanisms causing these artifacts, particularly in low-quality initialization scenarios, have not been fully explored. In this paper, we investigate the origins of floating artifacts from a frequency-domain perspective and identify under-optimized Gaussians as the primary source. Based on our analysis, we propose \textit{Eliminating-Floating-Artifacts} Gaussian Splatting (EFA-GS), which selectively expands under-optimized Gaussians to prioritize accurate low-frequency learning. Additionally, we introduce complementary depth-based and scale-based strategies to dynamically refine Gaussian expansion, effectively mitigating detail erosion. Extensive experiments on both synthetic and real-world datasets demonstrate that EFA-GS substantially reduces floating artifacts while preserving high-frequency details, achieving an improvement of 1.68 dB in PSNR over baseline method on our RWLQ dataset. Furthermore, we validate the effectiveness of our approach in downstream 3D editing tasks. Project Website: https://jcwang-gh.github.io/EFA-GS |
| title | Low-Frequency First: Eliminating Floating Artifacts in 3D Gaussian Splatting |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.02493 |