Monocular 3D bubble reconstruction: DNS-informed ray tracing and deep learning
Abstract
Bubble size, depth, and spatial distribution govern transport and uniformity in multiphase flows. A single shadowgraphic view cannot separate bubble diameter from focal-plane displacement, as image signatures depend on both, while multicamera systems add optical access, calibration, and cost. We develop a single-camera physics-guided framework combining direct numerical simulation (DNS), validated Monte Carlo ray tracing, preprocessing, and focus-conditioned multitask deep learning to recover three-dimensional bubble position and physical-equivalent diameter from two-dimensional shadowgraphs. DNS-resolved bubble label images rendered at multiple focal-plane settings. The ray tracer reproduces shadowgraphic signatures with errors below 3% (intensity), 1% (apparent size), 15% (blur), 6% (numerical aperture), and 4% (edge-spread-function shape), running ∼30× faster than the CPU implementation. The dataset has $900$ frames and 87,728 labeled instances, partitioned by DNS timestamp to prevent leakage and expanded to over 105 crops by broad-depth controlled-density rendering. A multitask network predicts signed depth and diameter from crops and focal-plane coordinates, achieving ∼97.6% normalized depth accuracy on held-out data; a closed-loop DNS-to-image-to-reconstruction test of $180$ bubbles gives diameter error below 9.71% (∼90.29% accuracy). On experimental images at four radial planes ($142−−971$ bubbles each), PDF overlap is 68%--92% and log-PDF correlation is $0.72−−0.87$. At the focal reference plane (11,679 bubbles), overlap is ∼86%, correlation is $0.93$, and full-distribution, D99.8, and composite errors are below 7.7%, increasing with focal-plane distance and defining a recoverability limit. Without stereoscopic hardware, the framework offers a scalable diagnostic for dense bubbly flows.
Related
- Physics-Informed Self-Supervised Learning for Joint Wire Calibration and Interaction Position Reconstruction in Multi-Wire Parallel Plate Avalanche Counters
- Prior-Guided Physics-Informed Deep Learning for Fast 4D MRI Reconstruction
- Learning Memory Operators with Physics-Informed Neural Networks: State Recovery, Kernel Reconstruction, and Parameter Identifiability
- Physics-informed, boundary-constrained Gaussian process regression for the reconstruction of fluid flow fields
- Reconstruction and Synthesis of Arbitrary Optical Intensity Patterns in Extremely Multimode Waveguide Cavities via Physics-Informed Optimized Modal Superposition
BibTeX
@misc{nayak2026monocular,
title = {{Monocular 3D bubble reconstruction: DNS-informed ray tracing and deep learning}},
author = {Chaitanya S. Nayak and Faizaan Mohammed and Vivek Kumar and Shivam Prajapati and Suhas S. Jain and Cyrus K. Aidun},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.28908},
eprint = {2610.28908},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.28908},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Monocular 3D bubble reconstruction: DNS-informed ray tracing and deep learning
AU - Chaitanya S. Nayak
AU - Faizaan Mohammed
AU - Vivek Kumar
AU - Shivam Prajapati
AU - Suhas S. Jain
AU - Cyrus K. Aidun
PY - 2026
DA - 2026/10/20
PB - arXiv
DO - 10.48550/arxiv.2610.28908
UR - https://arxiv.org/abs/2610.28908
AB - Bubble size, depth, and spatial distribution govern transport and uniformity in multiphase flows. A single shadowgraphic view cannot separate bubble diameter from focal-plane displacement, as image signatures depend on both, while multicamera systems add optical access, calibration, and cost. We develop a single-camera physics-guided framework combining direct numerical simulation (DNS), validated Monte Carlo ray tracing, preprocessing, and focus-conditioned multitask deep learning to recover three-dimensional bubble position and physical-equivalent diameter from two-dimensional shadowgraphs. DNS-resolved bubble label images rendered at multiple focal-plane settings. The ray tracer reproduces shadowgraphic signatures with errors below 3% (intensity), 1% (apparent size), 15% (blur), 6% (numerical aperture), and 4% (edge-spread-function shape), running ∼30× faster than the CPU implementation. The dataset has $900$ frames and 87,728 labeled instances, partitioned by DNS timestamp to prevent leakage and expanded to over 10^5 crops by broad-depth controlled-density rendering. A multitask network predicts signed depth and diameter from crops and focal-plane coordinates, achieving ∼97.6% normalized depth accuracy on held-out data; a closed-loop DNS-to-image-to-reconstruction test of $180$ bubbles gives diameter error below 9.71% (∼90.29% accuracy). On experimental images at four radial planes ($142−−971$ bubbles each), PDF overlap is 68%--92% and log-PDF correlation is $0.72−−0.87$. At the focal reference plane (11,679 bubbles), overlap is ∼86%, correlation is $0.93$, and full-distribution, D_99.8, and composite errors are below 7.7%, increasing with focal-plane distance and defining a recoverability limit. Without stereoscopic hardware, the framework offers a scalable diagnostic for dense bubbly flows.
ER -