Counting Contributions, Not Views: Occlusion-Aware Densification for 3D Gaussian Splatting
Overview & Synopsis
3D Gaussian Splatting grows a dense scene from a sparse initialization through adaptive density control (ADC), driven by per-Gaussian statistics gathered during rendering. These statistics pass a frustum-based visibility filter blind to occlusion: fully occluded Gaussians still count as observed, diluting the averaged gradient signal and suppressing densification precisely where geometry is occluded. We correct this with an occlusion-aware filter that restricts densification statistics to views in which a Gaussian actually contributes, and replace the criterion's raw view-count normalizer with an average-contribution one. Integrated into a StopThePop-based framework, the two together improve every image-quality metric over the occlusion-blind baseline on occlusion-heavy scenes (up to 6% lower LPIPS), at less than half the Gaussians a view-count normalizer requires. Under the longer schedules these large scenes require, the count stays bounded where most criteria diverge, and on smaller benchmarks our method stays competitive at a fraction of the competitors' count.
arxiv.org)
← / → for pages • + / - for zoom • 0 to fit width
Powered by Mozilla PDF.js v3.11
Document Information
| Document Title | Counting Contributions, Not Views: Occlusion-Aware Densification for 3D Gaussian Splatting |
|---|---|
| Author / Organization | Marcel Rogge, René Schuster, Didier Stricker |
| Subject & Discipline | cs.CV |
| Categories | Science & Mathematics |
| Publication Year | 2026 |
| License / Rights | arXiv Open Access / Creative Commons |
| Resource Verification | Listed PDF (Verification Pending) |
| Original Host Website |
arXiv
(arxiv.org)
|
| File Format | application/pdf (Portable Document Format) |
| Language | EN |
| Catalog ID | DOC-272143 |
| Original Source Link | Visit Source Page on arxiv.org » |