We propose high dynamic range (HDR) radiance fields, HDR-Plenoxels, that learn a plenoptic function of 3D HDR radiance fields, geometry information, and varying camera settings inherent in 2D low dynamic range (LDR) images. Our voxel-based volume rendering pipeline reconstructs HDR radiance fields with only multi-view LDR images taken from varying camera settings in an end-to-end manner and has a fast convergence speed. To deal with various cameras in real-world scenarios, we introduce a tone mapping module that models the digital in-camera imaging pipeline (ISP) and disentangles radiometric settings. Our tone mapping module allows us to render by controlling the radiometric settings of each novel view. Finally, we build a multi-view dataset with varying camera conditions, which fits our problem setting. Our experiments show that HDR-Plenoxels can express detail and high-quality HDR novel views from only LDR images with various cameras.
Cite
@article{arxiv.2208.06787,
title = {HDR-Plenoxels: Self-Calibrating High Dynamic Range Radiance Fields},
author = {Kim Jun-Seong and Kim Yu-Ji and Moon Ye-Bin and Tae-Hyun Oh},
journal= {arXiv preprint arXiv:2208.06787},
year = {2022}
}
Comments
Accepted at ECCV 2022. [Project page] https://hdr-plenoxels.github.io [Code] https://github.com/postech-ami/HDR-Plenoxels