NerfBaselines

Nerf
Baselines

NerfBaselines is a framework for evaluating and comparing existing NeRF methods. Currently, most official implementations use different dataset loaders, evaluation protocols, and metrics which renders the comparison of methods difficult. Therefore, this project aims to provide a unified interface for running and evaluating methods on different datasets in a consistent way using the same metrics. But instead of reimplementing the methods, we use the official implementations and wrap them so that they can be run easily using the same interface.

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.

Zip-NeRF5h 30m 49s26.19 GB
Mip-NeRF 3607h 29m 42s126.99 GB
Mip-Splatting25m 1s10.96 GB
Gaussian Splatting22m 45s11.12 GB
NerfStudio19m 50s3.80 GB
Tetra-NeRF17h 32m 35s13.37 GB
Instant NGP4m 16s5.62 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.

Zip-NeRF5h 21m 57s26.20 GB
Mip-Splatting6m 49s2.65 GB
Gaussian Splatting6m 6s3.08 GB
Instant NGP2m 23s2.57 GB
Tetra-NeRF6h 53m 20s29.57 GB
TensoRF8m 9s16.86 GB
Mip-NeRF 3603h 29m 39s114.80 GB
NerfStudio9m 38s3.65 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.

Zip-NeRF5h 21m 41s26.19 GB
Instant NGP4m 33s4.22 GB
NerfStudio13m 30s4.77 GB
Gaussian SplattingN/AN/A
Mip-SplattingN/AN/A