Datasets

Blender

NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis

Authors:
Ben Mildenhall, Pratul P. Srinivasan, Matthew Tancik, Jonathan T. Barron, Ravi Ramamoorthi, Ren Ng
Paper:

https://arxiv.org/pdf/2003.08934.pdf

Web:

https://www.matthewtancik.com/nerf

ID:
Blender
Evaluation protocol:

nerf (source code)

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. Scenes are licensed under various CC licenses.

LLFF

LLFF: A Large-Scale, Long-Form Video Dataset for 3D Scene Understanding

Authors:
Ben Mildenhall, Pratul P. Srinivasan, Rodrigo Ortiz-Cayon, Nima Khademi Kalantari, Ravi Ramamoorthi, Ren Ng, Abhishek Kar
Paper:

https://arxiv.org/pdf/1905.00889.pdf

Web:

https://bmild.github.io/llff/

ID:
LLFF
Evaluation protocol:

nerf (source code)

LLFF is a dataset of forward-facing scenes with a small variation in camera pose. NeRF methods usually use NDC-space parametrization for the scene representation.

Mip-NeRF 360

Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields

Authors:
Jonathan T. Barron, Ben Mildenhall, Dor Verbin, Pratul P. Srinivasan, Peter Hedman
Paper:

https://arxiv.org/pdf/2111.12077.pdf

Web:

https://jonbarron.info/mipnerf360/

ID:
Mip-NeRF 360
Evaluation protocol:

nerf (source code)

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.

Nerfstudio

Nerfstudio: A Modular Framework for Neural Radiance Field Development

Authors:
Matthew Tancik, Ethan Weber, Evonne Ng, Ruilong Li, Brent Yi, Justin Kerr, Terrance Wang, Alexander Kristoffersen, Jake Austin, Kamyar Salahi, Abhik Ahuja, David McAllister, Angjoo Kanazawa
Paper:

https://arxiv.org/pdf/2302.04264.pdf

Web:

https://nerf.studio

ID:
Nerfstudio
Evaluation protocol:

default (source code)

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.

Photo Tourism

Photo Tourism: Exploring Photo Collections in 3D

Authors:
Noah Snavely, Steven M. Seitz, Richard Szeliski
Paper:

https://phototour.cs.washington.edu/Photo_Tourism.pdf

Web:

https://phototour.cs.washington.edu/

ID:
Photo Tourism
Evaluation protocol:

nerfw (source code)

Photo Tourism is a dataset of images of famous landmarks, such as the Sacre Coeur, the Trevi Fountain, and the Brandenburg Gate. The images were captured by tourist at different times of the day and year, images have varying lighting conditions and occlusions. The evaluation protocol is based on NeRF-W, where the image appearance embeddings are optimized on the left side of the image and the metrics are computed on the right side of the image.

SeaThru-NeRF

SeaThru-NeRF: Neural Radiance Fields in Scattering Media

Authors:
Deborah Levy, Amit Peleg, Naama Pearl, Dan Rosenbaum, Derya Akkaynak, Tali Treibitz, Simon Korman
Paper:

https://openaccess.thecvf.com/content/CVPR2023/papers/Levy_SeaThru-NeRF_Neural_Radiance_Fields_in_Scattering_Media_CVPR_2023_paper.pdf

Web:

https://sea-thru-nerf.github.io/

Licenses:

Apache 2.0

ID:
SeaThru-NeRF
Evaluation protocol:

default (source code)

SeaThru-NeRF dataset contains four underwater forward-facing scenes.

Tanks and Temples

Tanks and Temples: Benchmarking Large-Scale Scene Reconstruction

Authors:
Arno Knapitsch, Jaesik Park, Qian-Yi Zhou, Vladlen Koltun
Paper:

https://storage.googleapis.com/t2-downloads/paper/tanks-and-temples.pdf

Web:

https://www.tanksandtemples.org/

ID:
Tanks and Temples
Evaluation protocol:

default (source code)

Tanks and Temples is a benchmark for image-based 3D reconstruction. The benchmark sequences were acquired outside the lab, in realistic conditions. Ground-truth data was captured using an industrial laser scanner. The benchmark includes both outdoor scenes and indoor environments. The dataset is split into three subsets: training, intermediate, and advanced.