Neural radiance fields (NeRFs) have demonstrated state-of-the-art performance for 3D computer vision tasks, including novel view synthesis and 3D shape reconstruction. However, these methods fail in adverse weather conditions. To address this challenge, we introduce DehazeNeRF as a framework that robustly operates in hazy conditions. DehazeNeRF extends the volume rendering equation by adding physically realistic terms that model atmospheric scattering. By parameterizing these terms using suitable networks that match the physical properties, we introduce effective inductive biases, which, together with the proposed regularizations, allow DehazeNeRF to demonstrate successful multi-view haze removal, novel view synthesis, and 3D shape reconstruction where existing approaches fail.
@article{arxiv.2303.11364,
title = {DehazeNeRF: Multiple Image Haze Removal and 3D Shape Reconstruction using Neural Radiance Fields},
author = {Wei-Ting Chen and Wang Yifan and Sy-Yen Kuo and Gordon Wetzstein},
journal= {arXiv preprint arXiv:2303.11364},
year = {2023}
}
Comments
including supplemental material; project page: https://www.computationalimaging.org/publications/dehazenerf