Non-uniform Sampling Strategies for NeRF on 360° images
Takashi Otonari (The University of Tokyo),* Satoshi Ikehata (National Institute of Informatics), Kiyoharu Aizawa (The University of Tokyo)
The 33rd British Machine Vision Conference
Abstract
In recent years, the performance of novel view synthesis using perspective images has dramatically improved with the advent of neural radiance fields (NeRF). This study proposes two novel techniques that effectively build NeRF for 360° omnidirectional images. Due to the characteristics of a 360° image of ERP format that has spatial distortion in their high latitude regions and a 360° wide viewing angle, NeRF’s general ray sampling strategy is ineffective. Hence, the view synthesis accuracy of NeRF is limited and learning is not efficient. We propose two non-uniform ray sampling schemes for NeRF to suit 360° images – distortion-aware ray sampling and content-aware ray sampling. We created an evaluation dataset Synth360 using Replica and SceneCity models of indoor and outdoor scenes, respectively. In experiments, we show that our proposal successfully builds 360° image NeRF in terms of both accuracy and efficiency. The proposal is widely applicable to advanced variants of NeRF. DietNeRF, AugNeRF, and NeRF++ combined with the proposed techniques further improve the performance. Moreover, we show that our proposed method enhances the quality of real-world scenes in 360° images. Synth360: https://drive.google.com/drive/folders/1suL9B7DO2no21ggiIHkH3JF3OecasQLb.Video
Citation
@inproceedings{Otonari_2022_BMVC,
author = { Takashi Otonari and Satoshi Ikehata and Kiyoharu Aizawa},
title = {Non-uniform Sampling Strategies for NeRF on 360° 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/0344.pdf}
}
Copyright © 2022
The British Machine Vision Conference is organised by