Zip-NeRF
Zip-NeRF is a radiance field method which addresses the aliasing problem in the case of hash-grid based methods (iNGP-based). Instead of sampling along the ray it samples along a spiral path - approximating integration along the frustum.
Mip-NeRF 360
Mip-NeRF 360 is a collection of four indoor and five outdoor object-centric scenes. The camera trajectory is an orbit around the object with fixed elevation and radius. The test set takes each n-th frame of the trajectory as test views.
Scene | PSNR | SSIM | LPIPS | Time | GPU Mem. | |
|---|---|---|---|---|---|---|
| average | 5h 30m 49s | 26.19 GB |
Blender
Blender (nerf-synthetic) is a synthetic dataset used to benchmark NeRF methods. It consists of 8 scenes of an object placed on a white background. Cameras are placed on a semi-sphere around the object.
Scene | PSNR | SSIM | LPIPS | Time | GPU Mem. | |
|---|---|---|---|---|---|---|
| average | 5h 21m 57s | 26.20 GB |
Nerfstudio
Nerfstudio Dataset includes 10 in-the-wild captures obtained using either a mobile phone or a mirror-less camera with a fisheye lens. We processed the data using either COLMAP or the Polycam app to obtain camera poses and intrinsic parameters.
Scene | PSNR | SSIM | LPIPS | Time | GPU Mem. | |
|---|---|---|---|---|---|---|
| average | 5h 21m 41s | 26.19 GB |