Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2403.14166 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917804788154368 |
|---|---|
| author | Fang, Guangchi Wang, Bing |
| author_facet | Fang, Guangchi Wang, Bing |
| contents | In this study, we explore the challenge of efficiently representing scenes with a constrained number of Gaussians. Our analysis shifts from traditional graphics and 2D computer vision to the perspective of point clouds, highlighting the inefficient spatial distribution of Gaussian representation as a key limitation in model performance. To address this, we introduce strategies for densification including blur split and depth reinitialization, and simplification through intersection preserving and sampling. These techniques reorganize the spatial positions of the Gaussians, resulting in significant improvements across various datasets and benchmarks in terms of rendering quality, resource consumption, and storage compression. Our Mini-Splatting integrates seamlessly with the original rasterization pipeline, providing a strong baseline for future research in Gaussian-Splatting-based works. \href{https://github.com/fatPeter/mini-splatting}{Code is available}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_14166 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Mini-Splatting: Representing Scenes with a Constrained Number of Gaussians Fang, Guangchi Wang, Bing Computer Vision and Pattern Recognition In this study, we explore the challenge of efficiently representing scenes with a constrained number of Gaussians. Our analysis shifts from traditional graphics and 2D computer vision to the perspective of point clouds, highlighting the inefficient spatial distribution of Gaussian representation as a key limitation in model performance. To address this, we introduce strategies for densification including blur split and depth reinitialization, and simplification through intersection preserving and sampling. These techniques reorganize the spatial positions of the Gaussians, resulting in significant improvements across various datasets and benchmarks in terms of rendering quality, resource consumption, and storage compression. Our Mini-Splatting integrates seamlessly with the original rasterization pipeline, providing a strong baseline for future research in Gaussian-Splatting-based works. \href{https://github.com/fatPeter/mini-splatting}{Code is available}. |
| title | Mini-Splatting: Representing Scenes with a Constrained Number of Gaussians |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.14166 |