Faster 3D Gaussian Splatting Convergence via Structure-Aware Densification
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910180836376576 |
|---|---|
| author | Lyu, Linjie Tewari, Ayush Chen, Jianchun Leimkühler, Thomas Theobalt, Christian |
| author_facet | Lyu, Linjie Tewari, Ayush Chen, Jianchun Leimkühler, Thomas Theobalt, Christian |
| contents | 3D Gaussian Splatting has emerged as a powerful scene representation for real-time novel-view synthesis. However, its standard adaptive density control relies on screen-space positional gradients, which do not distinguish between geometric misplacement and frequency aliasing, often leading to either over-blurred high-frequency textures or inefficient over-densification. We present a structure-aware densification framework. Our key insight is that the decision to subdivide a Gaussian should be driven by an explicit comparison between its projected screen-space extent and the local structure of the texture it seeks to represent. We introduce a multi-scale frequency analysis combining structure tensors with Laplacian scale space analysis to estimate the dominant frequency at each pixel, enabling robust supervision across varying texture scales. Based on this analysis, we define $η$, a per-Gaussian, per-axis frequency violation metric that indicates when a primitive may be under-resolving local texture details. Unlike methods that perform isotropic splitting (e.g., splitting each Gaussian into two smaller ones with uniform shape), our approach performs anisotropic splitting. For each axis with high $η$, we compute a split factor to better resolve the local frequency content. We further introduce a multiview consistency criterion that aggregates $η$ observations across multiple views. By performing densification early and faster, we skip the lengthy iterative densification phases required by baseline methods and achieve significantly faster convergence. Experiments on standard benchmarks demonstrate that our method also achieves superior reconstruction quality, particularly in high-frequency regions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_28016 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Faster 3D Gaussian Splatting Convergence via Structure-Aware Densification Lyu, Linjie Tewari, Ayush Chen, Jianchun Leimkühler, Thomas Theobalt, Christian Computer Vision and Pattern Recognition Graphics Machine Learning 3D Gaussian Splatting has emerged as a powerful scene representation for real-time novel-view synthesis. However, its standard adaptive density control relies on screen-space positional gradients, which do not distinguish between geometric misplacement and frequency aliasing, often leading to either over-blurred high-frequency textures or inefficient over-densification. We present a structure-aware densification framework. Our key insight is that the decision to subdivide a Gaussian should be driven by an explicit comparison between its projected screen-space extent and the local structure of the texture it seeks to represent. We introduce a multi-scale frequency analysis combining structure tensors with Laplacian scale space analysis to estimate the dominant frequency at each pixel, enabling robust supervision across varying texture scales. Based on this analysis, we define $η$, a per-Gaussian, per-axis frequency violation metric that indicates when a primitive may be under-resolving local texture details. Unlike methods that perform isotropic splitting (e.g., splitting each Gaussian into two smaller ones with uniform shape), our approach performs anisotropic splitting. For each axis with high $η$, we compute a split factor to better resolve the local frequency content. We further introduce a multiview consistency criterion that aggregates $η$ observations across multiple views. By performing densification early and faster, we skip the lengthy iterative densification phases required by baseline methods and achieve significantly faster convergence. Experiments on standard benchmarks demonstrate that our method also achieves superior reconstruction quality, particularly in high-frequency regions. |
| title | Faster 3D Gaussian Splatting Convergence via Structure-Aware Densification |
| topic | Computer Vision and Pattern Recognition Graphics Machine Learning |
| url | https://arxiv.org/abs/2604.28016 |