From NeRFs to Gaussian Splats, and Back
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910564494606336 |
|---|---|
| author | He, Siming Osman, Zach Chaudhari, Pratik |
| author_facet | He, Siming Osman, Zach Chaudhari, Pratik |
| contents | For robotics applications where there is a limited number of (typically ego-centric) views, parametric representations such as neural radiance fields (NeRFs) generalize better than non-parametric ones such as Gaussian splatting (GS) to views that are very different from those in the training data; GS however can render much faster than NeRFs. We develop a procedure to convert back and forth between the two. Our approach achieves the best of both NeRFs (superior PSNR, SSIM, and LPIPS on dissimilar views, and a compact representation) and GS (real-time rendering and ability for easily modifying the representation); the computational cost of these conversions is minor compared to training the two from scratch. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_09717 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | From NeRFs to Gaussian Splats, and Back He, Siming Osman, Zach Chaudhari, Pratik Computer Vision and Pattern Recognition For robotics applications where there is a limited number of (typically ego-centric) views, parametric representations such as neural radiance fields (NeRFs) generalize better than non-parametric ones such as Gaussian splatting (GS) to views that are very different from those in the training data; GS however can render much faster than NeRFs. We develop a procedure to convert back and forth between the two. Our approach achieves the best of both NeRFs (superior PSNR, SSIM, and LPIPS on dissimilar views, and a compact representation) and GS (real-time rendering and ability for easily modifying the representation); the computational cost of these conversions is minor compared to training the two from scratch. |
| title | From NeRFs to Gaussian Splats, and Back |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2405.09717 |