2DGH: 2D Gaussian-Hermite Splatting for High-quality Rendering and Better Geometry Reconstruction
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916375441702912 |
|---|---|
| author | Yu, Ruihan Huang, Tianyu Ling, Jingwang Xu, Feng |
| author_facet | Yu, Ruihan Huang, Tianyu Ling, Jingwang Xu, Feng |
| contents | 2D Gaussian Splatting has recently emerged as a significant method in 3D reconstruction, enabling novel view synthesis and geometry reconstruction simultaneously. While the well-known Gaussian kernel is broadly used, its lack of anisotropy and deformation ability leads to dim and vague edges at object silhouettes, limiting the reconstruction quality of current Gaussian splatting methods. To enhance the representation power, we draw inspiration from quantum physics and propose to use the Gaussian-Hermite kernel as the new primitive in Gaussian splatting. The new kernel takes a unified mathematical form and extends the Gaussian function, which serves as the zero-rank term in the updated formulation. Our experiments demonstrate the extraordinary performance of Gaussian-Hermite kernel in both geometry reconstruction and novel-view synthesis tasks. The proposed kernel outperforms traditional Gaussian Splatting kernels, showcasing its potential for high-quality 3D reconstruction and rendering. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_16982 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | 2DGH: 2D Gaussian-Hermite Splatting for High-quality Rendering and Better Geometry Reconstruction Yu, Ruihan Huang, Tianyu Ling, Jingwang Xu, Feng Computer Vision and Pattern Recognition Graphics 2D Gaussian Splatting has recently emerged as a significant method in 3D reconstruction, enabling novel view synthesis and geometry reconstruction simultaneously. While the well-known Gaussian kernel is broadly used, its lack of anisotropy and deformation ability leads to dim and vague edges at object silhouettes, limiting the reconstruction quality of current Gaussian splatting methods. To enhance the representation power, we draw inspiration from quantum physics and propose to use the Gaussian-Hermite kernel as the new primitive in Gaussian splatting. The new kernel takes a unified mathematical form and extends the Gaussian function, which serves as the zero-rank term in the updated formulation. Our experiments demonstrate the extraordinary performance of Gaussian-Hermite kernel in both geometry reconstruction and novel-view synthesis tasks. The proposed kernel outperforms traditional Gaussian Splatting kernels, showcasing its potential for high-quality 3D reconstruction and rendering. |
| title | 2DGH: 2D Gaussian-Hermite Splatting for High-quality Rendering and Better Geometry Reconstruction |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2408.16982 |