Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2412.03378 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916747213275136 |
|---|---|
| author | Talegaonkar, Chinmay Belhe, Yash Ramamoorthi, Ravi Antipa, Nicholas |
| author_facet | Talegaonkar, Chinmay Belhe, Yash Ramamoorthi, Ravi Antipa, Nicholas |
| contents | Recently, 3D Gaussian Splatting (3DGS) has enabled photorealistic view synthesis at high inference speeds. However, its splatting-based rendering model makes several approximations to the rendering equation, reducing physical accuracy. We show that the core approximations in splatting are unnecessary, even within a rasterizer; We instead volumetrically integrate 3D Gaussians directly to compute the transmittance across them analytically. We use this analytic transmittance to derive more physically-accurate alpha values than 3DGS, which can directly be used within their framework. The result is a method that more closely follows the volume rendering equation (similar to ray-tracing) while enjoying the speed benefits of rasterization. Our method represents opaque surfaces with higher accuracy and fewer points than 3DGS. This enables it to outperform 3DGS for view synthesis (measured in SSIM and LPIPS). Being volumetrically consistent also enables our method to work out of the box for tomography. We match the state-of-the-art 3DGS-based tomography method with fewer points. Our code is publicly available at: https://github.com/chinmay0301ucsd/Vol3DGS |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_03378 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Volumetrically Consistent 3D Gaussian Rasterization Talegaonkar, Chinmay Belhe, Yash Ramamoorthi, Ravi Antipa, Nicholas Computer Vision and Pattern Recognition Recently, 3D Gaussian Splatting (3DGS) has enabled photorealistic view synthesis at high inference speeds. However, its splatting-based rendering model makes several approximations to the rendering equation, reducing physical accuracy. We show that the core approximations in splatting are unnecessary, even within a rasterizer; We instead volumetrically integrate 3D Gaussians directly to compute the transmittance across them analytically. We use this analytic transmittance to derive more physically-accurate alpha values than 3DGS, which can directly be used within their framework. The result is a method that more closely follows the volume rendering equation (similar to ray-tracing) while enjoying the speed benefits of rasterization. Our method represents opaque surfaces with higher accuracy and fewer points than 3DGS. This enables it to outperform 3DGS for view synthesis (measured in SSIM and LPIPS). Being volumetrically consistent also enables our method to work out of the box for tomography. We match the state-of-the-art 3DGS-based tomography method with fewer points. Our code is publicly available at: https://github.com/chinmay0301ucsd/Vol3DGS |
| title | Volumetrically Consistent 3D Gaussian Rasterization |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.03378 |