摘要
3D Gaussian Splatting (3DGS) has emerged as a groundbreaking technique in the realm of photorealistic and real-time novel view rendering, garnering significant attention across diverse disciplines, including photogrammetry, remote sensing, and computer vision. Despite its remarkable capabilities, 3DGS encounters substantial challenges when applied to scenarios involving glossy or reflective materials, which exhibit pronounced variations in appearance from different viewing angles. To address this limitation, we introduce Glossy-Gaussian, a plug-and-play integration based on 3DGS for glossy scene reconstruction with real-time synthesis. Specifically, we enhance the view-adaptive spherical harmonic (SH)-based Gaussian kernel to introduce anisotropy to the transparency field, enabling the Gaussian field to accurately represent smooth and specular reflective regions without compromising rendering speed. Furthermore, we extend the capabilities of this Gaussian kernel to incorporate rotation and scaling, facilitating the directional decoding of both properties at the same Gaussian position. Our experimental results demonstrate that our approach significantly improves rendering quality in glossy scenes, as evidenced by increases in PSNR, SSIM, and LPIPS values, and achieves state-of-the-art performance compared to existing methods.
| 源语言 | 英语 |
|---|---|
| 页(从-至) | 886-890 |
| 页数 | 5 |
| 期刊 | IEEE Signal Processing Letters |
| 卷 | 32 |
| DOI | |
| 出版状态 | 已出版 - 1月 2025 |
基金资助
This work wassupported by the National Natural Science Foundation of China under Grant 42301507 and in part by the Natural Science Foundation of Hubei Province, China, under Grant 2022CFB727.
关键词
- Rendering (computer graphics)
- Kernel
- Anisotropic
- Image color analysis
- Harmonic analysis
- Training
- Neural radiance field
- Three-dimensional displays
- Lighting
- Covariance matrices
- 3D Gaussian splatting (3DGS)
- novel view rendering
- glossy materials
- adaptive anisotropic Gaussians
收录
- SCIE
- EI
- Scopus
学术指纹
探究 'Glossy-Gaussian: Adaptive Anisotropic Gaussians for View-Dependent Appearances' 的科研主题。它们共同构成独一无二的学术指纹。引用此
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver