CARVIEW

MOTORHOMES

Select Language

HTTP/2 200 server: GitHub.com content-type: text/html; charset=utf-8 last-modified: Mon, 25 Oct 2021 01:44:10 GMT access-control-allow-origin: * strict-transport-security: max-age=31556952 etag: W/"61760bea-346c" expires: Sat, 27 Dec 2025 21:33:28 GMT cache-control: max-age=600 content-encoding: gzip x-proxy-cache: MISS x-github-request-id: 30FB:2F7ECD:705F2A:7D7D9D:69504E50 accept-ranges: bytes age: 0 date: Sat, 27 Dec 2025 21:23:28 GMT via: 1.1 varnish x-served-by: cache-bom-vanm7210049-BOM x-cache: MISS x-cache-hits: 0 x-timer: S1766870608.352947,VS0,VE202 vary: Accept-Encoding x-fastly-request-id: a15e4f751780a9d2b9f7a7983106ca7a76e55505 content-length: 2694 NeRF in the Wild

NeRF in the Wild

Neural Radiance Fields for Unconstrained Photo Collections

CVPR 2021 (Oral)

Ricardo Martin-Brualla*

Google Research, Seattle

Google Research, Berlin

Google Research, San Francisco

Google Research, Berlin

[Paper]

Brandenburg Gate

Sacre Coeur

Trevi Fountain

Overview

Appearance Embedding Interpolation

NeRF-W captures lighting and photometric post-processing in a low-dimensional latent embedding space. Interpolating between two embeddings smoothly captures variation in appearance without affecting 3D geometry.

Geometric Consistency

NeRF-W disentangles lighting from the underlying 3D scene geometry. The latter remains consistent even as the former changes. Also available in 1080p and QHD.

Citation

@inproceedings{martinbrualla2020nerfw, author = {Martin-Brualla, Ricardo and Radwan, Noha and Sajjadi, Mehdi S. M. and Barron, Jonathan T. and Dosovitskiy, Alexey and Duckworth, Daniel}, title = {{NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections}}, booktitle = {CVPR}, year={2021} }

Additional links

Find a tab-separated list of filenames used for training and evaluation here: Brandenburg Gate, Sacre Coeur, Trevi Fountain, Hagia Sophia, Prague Old Town, and Taj Mahal.

Original Source | Taken Source