Neural Refractive Index Primitives for Flame Field Reconstruction Using Background-Oriented Schlieren

TL;DR

This paper introduces an advanced neural method for 3D flame field reconstruction using background-oriented schlieren, achieving high-resolution, robust, and efficient results with a novel neural primitive approach.

Contribution

The authors present a neural refractive-index-primitive method with multiresolution encoding and specialized losses for fast, high-quality 3D flame reconstruction, outperforming existing techniques.

Findings

Accurate recovery of large-scale and fine-scale flame structures

Robustness to noise demonstrated on real and simulated data

Faster convergence and higher resolution compared to prior methods

Abstract

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.