Computational imaging through turbid, bubbly and flowing water near the telescope
Abstract
Cameras in the surf zone or behind ship wakes look through turbid, bubbly, moving water close to the lens, yet restoration networks are usually scored only on displayed images. We introduce a measured dataset of a telescope viewing displayed images and physical objects through a 25~mm water layer 45~mm in front of its objective, under seven combinations of flow, bubbles and turbidity, with clear-water recordings as a second reference. Because the suspension scatters light far outside the 1.3\textdegree{} field of view, turbidity mainly removes contrast, 4.4- to 4.8-fold on a Siemens star. Restoring the mean of eight frames improves structural similarity (SSIM) by 0.032 over a single frame, and learned fusion of the frames adds little. One raw frame supports five-category recognition (96.8\%) as well as restored images. Adding synthetic training pairs leaves display-image scores unchanged but raises the correlation of a restored Siemens star with its clear-water recording from below 0.5 to above 0.9. These networks also improve ordinary underwater photographs without retraining, where training on measured pairs alone fails. Scoring against the digital source or a clear-water recording reverses the ranking of raw and restored images. These results support a simple pipeline: average the frames, classify raw frames directly, and restore with networks trained on measured and synthetic pairs.
Related
- Enhancing analytical photon transport in turbid media through physics-guided neural network corrections
- Quantum Computing through Computational Imaging: Representations, Measurement, and Inference
- Unveiling the stress field in a flowing complex fluid with velocity and microstructure imaging
- The James Webb Space Telescope Absolute Flux Calibration. VI. Near-infrared Camera Imaging and Coronagraphy
- Imaging exoplanets below the telescope stability limit
BibTeX
@misc{ingold2026computational,
title = {{Computational imaging through turbid, bubbly and flowing water near the telescope}},
author = {Alexander Ingold and Sabina D. Menon and Aadhi Umamageswaran and Alec Ikei and May H. Hlaing and Syed N. Qadri and Rajesh Menon},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.32646},
eprint = {2610.32646},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.32646},
}
RIS
TY - UNPB
TI - Computational imaging through turbid, bubbly and flowing water near the telescope
AU - Alexander Ingold
AU - Sabina D. Menon
AU - Aadhi Umamageswaran
AU - Alec Ikei
AU - May H. Hlaing
AU - Syed N. Qadri
AU - Rajesh Menon
PY - 2026
DA - 2026/10/23
PB - arXiv
DO - 10.48550/arxiv.2610.32646
UR - https://arxiv.org/abs/2610.32646
AB - Cameras in the surf zone or behind ship wakes look through turbid, bubbly, moving water close to the lens, yet restoration networks are usually scored only on displayed images. We introduce a measured dataset of a telescope viewing displayed images and physical objects through a 25~mm water layer 45~mm in front of its objective, under seven combinations of flow, bubbles and turbidity, with clear-water recordings as a second reference. Because the suspension scatters light far outside the 1.3\textdegree{} field of view, turbidity mainly removes contrast, 4.4- to 4.8-fold on a Siemens star. Restoring the mean of eight frames improves structural similarity (SSIM) by 0.032 over a single frame, and learned fusion of the frames adds little. One raw frame supports five-category recognition (96.8\%) as well as restored images. Adding synthetic training pairs leaves display-image scores unchanged but raises the correlation of a restored Siemens star with its clear-water recording from below 0.5 to above 0.9. These networks also improve ordinary underwater photographs without retraining, where training on measured pairs alone fails. Scoring against the digital source or a clear-water recording reverses the ranking of raw and restored images. These results support a simple pipeline: average the frames, classify raw frames directly, and restore with networks trained on measured and synthetic pairs.
ER -