Zip-NeRF
ZipNeRF is a dataset with four large scenes: Berlin, Alameda, London, and NYC, (1000-2000 photos each) captured using fisheye cameras. This implementation uses undistorted images which are provided with the dataset and the downsampled resolutions are between 1392 × 793 and 2000 × 1140 depending on scene. It is recommended to use exposure modeling with this dataset if available.
Authors: Jonathan T. Barron, Ben Mildenhall, Dor Verbin, Pratul P. Srinivasan, Peter Hedman
Octree-GS | 22.33 | 0.762 | 0.473 | 44m 56s | 27.63 GB |
PSNR
Peak Signal to Noise Ratio. The higher the better.
Octree-GS | 22.79 | 13.64 | 25.76 | 27.13 |
SSIM
Structural Similarity Index. The higher the better. The implementation matches JAX's SSIM and torchmetrics's SSIM (with default parameters).
Octree-GS | 0.730 | 0.669 | 0.807 | 0.841 |
LPIPS (VGG)
Learned Perceptual Image Patch Similarity. The lower the better. The implementation uses VGG backbone and matches lpips pip package with checkpoint version 0.1
Octree-GS | 0.448 | 0.640 | 0.433 | 0.372 |