Casual Indoor HDR Radiance Capture from Omnidirectional Images
Pulkit Gera (CVIT,IIIT),* Mohammad Reza Karimi Dastjerdi (Université Laval), Charles Renaud (Université Laval), P. J. Narayanan (IIIT-Hyderabad), Jean-Francois Lalonde (Laval University)
The 33rd British Machine Vision Conference
Abstract
We present PanoHDR-NeRF, a neural representation of the full HDR radiance field of an indoor scene, and a pipeline to capture it casually, without elaborate setups or complex capture protocols. First, a user captures a low dynamic range (LDR) omnidirectional video of the scene by freely waving an off-the-shelf camera around the scene. Then, an LDR2HDR network uplifts the captured LDR frames to HDR, which are used to train a tailored NeRF++ model. The resulting PanoHDR-NeRF can render full HDR images from any location of the scene. Through experiments on a novel test dataset of real scenes with the ground truth HDR radiance captured at locations not seen during training, we show that PanoHDR-NeRF predicts plausible HDR radiance from any scene point. We also show that the predicted radiance can synthesize correct lighting effects, enabling the augmentation of indoor scenes with synthetic objects that are lit correctly. Datasets and code are available at https://lvsn.github.io/PanoHDR-NeRF/.Video
Citation
@inproceedings{Gera_2022_BMVC,
author = {Pulkit Gera and Mohammad Reza Karimi Dastjerdi and Charles Renaud and P. J. Narayanan and Jean-Francois Lalonde},
title = {Casual Indoor HDR Radiance Capture from Omnidirectional Images},
booktitle = {33rd British Machine Vision Conference 2022, {BMVC} 2022, London, UK, November 21-24, 2022},
publisher = {{BMVA} Press},
year = {2022},
url = {https://bmvc2022.mpi-inf.mpg.de/0305.pdf}
}
Copyright © 2022
The British Machine Vision Conference is organised by