TransparentGS: Fast Inverse Rendering of Transparent Objects with Gaussians
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909597954998272 |
|---|---|
| author | Huang, Letian Ye, Dongwei Dan, Jialin Tao, Chengzhi Liu, Huiwen Zhou, Kun Ren, Bo Li, Yuanqi Guo, Yanwen Guo, Jie |
| author_facet | Huang, Letian Ye, Dongwei Dan, Jialin Tao, Chengzhi Liu, Huiwen Zhou, Kun Ren, Bo Li, Yuanqi Guo, Yanwen Guo, Jie |
| contents | The emergence of neural and Gaussian-based radiance field methods has led to considerable advancements in novel view synthesis and 3D object reconstruction. Nonetheless, specular reflection and refraction continue to pose significant challenges due to the instability and incorrect overfitting of radiance fields to high-frequency light variations. Currently, even 3D Gaussian Splatting (3D-GS), as a powerful and efficient tool, falls short in recovering transparent objects with nearby contents due to the existence of apparent secondary ray effects. To address this issue, we propose TransparentGS, a fast inverse rendering pipeline for transparent objects based on 3D-GS. The main contributions are three-fold. Firstly, an efficient representation of transparent objects, transparent Gaussian primitives, is designed to enable specular refraction through a deferred refraction strategy. Secondly, we leverage Gaussian light field probes (GaussProbe) to encode both ambient light and nearby contents in a unified framework. Thirdly, a depth-based iterative probes query (IterQuery) algorithm is proposed to reduce the parallax errors in our probe-based framework. Experiments demonstrate the speed and accuracy of our approach in recovering transparent objects from complex environments, as well as several applications in computer graphics and vision. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_18768 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TransparentGS: Fast Inverse Rendering of Transparent Objects with Gaussians Huang, Letian Ye, Dongwei Dan, Jialin Tao, Chengzhi Liu, Huiwen Zhou, Kun Ren, Bo Li, Yuanqi Guo, Yanwen Guo, Jie Graphics Computer Vision and Pattern Recognition The emergence of neural and Gaussian-based radiance field methods has led to considerable advancements in novel view synthesis and 3D object reconstruction. Nonetheless, specular reflection and refraction continue to pose significant challenges due to the instability and incorrect overfitting of radiance fields to high-frequency light variations. Currently, even 3D Gaussian Splatting (3D-GS), as a powerful and efficient tool, falls short in recovering transparent objects with nearby contents due to the existence of apparent secondary ray effects. To address this issue, we propose TransparentGS, a fast inverse rendering pipeline for transparent objects based on 3D-GS. The main contributions are three-fold. Firstly, an efficient representation of transparent objects, transparent Gaussian primitives, is designed to enable specular refraction through a deferred refraction strategy. Secondly, we leverage Gaussian light field probes (GaussProbe) to encode both ambient light and nearby contents in a unified framework. Thirdly, a depth-based iterative probes query (IterQuery) algorithm is proposed to reduce the parallax errors in our probe-based framework. Experiments demonstrate the speed and accuracy of our approach in recovering transparent objects from complex environments, as well as several applications in computer graphics and vision. |
| title | TransparentGS: Fast Inverse Rendering of Transparent Objects with Gaussians |
| topic | Graphics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.18768 |