3D-HGS: 3D Half-Gaussian Splatting
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_ | 1866910928410247168 |
|---|---|
| author | Li, Haolin Liu, Jinyang Sznaier, Mario Camps, Octavia |
| author_facet | Li, Haolin Liu, Jinyang Sznaier, Mario Camps, Octavia |
| contents | Photo-realistic image rendering from 3D scene reconstruction has advanced significantly with neural rendering techniques. Among these, 3D Gaussian Splatting (3D-GS) outperforms Neural Radiance Fields (NeRFs) in quality and speed but struggles with shape and color discontinuities. We propose 3D Half-Gaussian (3D-HGS) kernels as a plug-and-play solution to address these limitations. Our experiments show that 3D-HGS enhances existing 3D-GS methods, achieving state-of-the-art rendering quality without compromising speed. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_02720 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | 3D-HGS: 3D Half-Gaussian Splatting Li, Haolin Liu, Jinyang Sznaier, Mario Camps, Octavia Computer Vision and Pattern Recognition Graphics Photo-realistic image rendering from 3D scene reconstruction has advanced significantly with neural rendering techniques. Among these, 3D Gaussian Splatting (3D-GS) outperforms Neural Radiance Fields (NeRFs) in quality and speed but struggles with shape and color discontinuities. We propose 3D Half-Gaussian (3D-HGS) kernels as a plug-and-play solution to address these limitations. Our experiments show that 3D-HGS enhances existing 3D-GS methods, achieving state-of-the-art rendering quality without compromising speed. |
| title | 3D-HGS: 3D Half-Gaussian Splatting |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2406.02720 |