Neural refractive index primitives for flame field reconstruction using background-oriented schlieren
Combustion and Flame · 2026-08 · 290 · 115082
DOI: 10.1016/j.combustflame.2026.115082 ↗Kurz gefasst
Fachartikel in der Zeitschrift Combustion and Flame, 2026-08. Verfasst von Xinyi Lu und 5 weiteren Autor:innen. Die Arbeit nennt 23 Literaturangaben. Gefördert von: Zhejiang Province Natural Science Foundation.
Abstract (Originalsprache)
An improved neural refractive-index-primitive method for background-oriented schlieren tomography is presented, enabling continuous three-dimensional reconstruction of refractive-index fields using a compact multilayer perceptron. The method adopts the refractive-index field as the sole neural primitive and integrates multiresolution hash encoding, automatic-discrete gradient losses, and a three-dimensional mask to enable fast convergence and high-resolution, spatially coherent reconstructions. Tests on numerical combustion phantoms and real flame data demonstrate accurate recovery of both large-scale structures and fine-scale turbulence, strong robustness to noise, and clear advantages over frequency-encoding-based and voxel-based reconstruction methods.
Förderung
- Zhejiang Province Natural Science Foundation
Zitieren
APA
Lu, X., Hu, W., Liao, Z., Wang, Z., Zhang, Y., & Li, J. (2026). Neural refractive index primitives for flame field reconstruction using background-oriented schlieren. Combustion and Flame, 290, 115082. https://doi.org/10.1016/j.combustflame.2026.115082
Vancouver
Lu X, Hu W, Liao Z, Wang Z, Zhang Y, Li J. Neural refractive index primitives for flame field reconstruction using background-oriented schlieren. Combustion and Flame. 2026;290:115082. doi:10.1016/j.combustflame.2026.115082
BibTeX
@article{Lu2026,
author = {Lu, Xinyi and Hu, Wei and Liao, Zizhou and Wang, Zheng and Zhang, Yue and Li, Jingxuan},
title = {Neural refractive index primitives for flame field reconstruction using background-oriented schlieren},
journal = {Combustion and Flame},
year = {2026},
volume = {290},
pages = {115082},
doi = {10.1016/j.combustflame.2026.115082}
}
EUVIMED