NeRF in the Wild

Neural Radiance Fields for Unconstrained Photo Collections

CVPR 2021 (Oral)

Google Research, Seattle

Google Research, Berlin

Google Research, Berlin

Google Research, San Francisco

Google Research, Berlin

Google Research, Berlin

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} }