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.