Underwater image restoration is challenging because wavelength-dependent absorption, scattering, and turbidity reduce visibility and distort color. Sea-Thru uses scene-depth information to compensate for attenuation and backscatter; however, optical depth-estimation methods may become unreliable in turbid water. This work investigates the integration of sonar-derived depth maps into Sea-Thru. Since acoustic sensing is less affected by turbidity, sonar provides an alternative source of depth information when optical methods perform poorly.
Underwater Image Reconstruction Using Sea-Thru With Sonar-Derived Depth Maps / Mashaallah, Z., Del Prete, A., Amato, F.. - (2026), pp. 748-749. (22nd IEEE International Conference on eScience Naples, Italy 28 September 2026 - 02 October 2026) [10.1109/escience70237.2026.00101].
Underwater Image Reconstruction Using Sea-Thru With Sonar-Derived Depth Maps
Mashaallah, Zahida;Del Prete, Alessandro;Amato, Flora
2026
Abstract
Underwater image restoration is challenging because wavelength-dependent absorption, scattering, and turbidity reduce visibility and distort color. Sea-Thru uses scene-depth information to compensate for attenuation and backscatter; however, optical depth-estimation methods may become unreliable in turbid water. This work investigates the integration of sonar-derived depth maps into Sea-Thru. Since acoustic sensing is less affected by turbidity, sonar provides an alternative source of depth information when optical methods perform poorly.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.


