Seafloor-Invariant Caustics Removal From Underwater Imagery

Mapping the seafloor with underwater imaging cameras is of significant importance for various applications including marine engineering, geology, geomorphology, archaeology, and biology. For shallow waters, among the underwater imaging challenges, caustics, i.e., the complex physical phenomena resulting from the projection of light rays being refracted by the wavy surface, is likely the most crucial one. Caustics is the main factor during underwater imaging campaigns that massively degrades image quality and affects severely any 2-D mosaicking or 3-D reconstruction of the seabed. In this article, we propose a novel method for correcting the radiometric effects of caustics on shallow underwater imagery. Contrary to the state-of-the-art, the developed method can handle the seabed and riverbed of any anaglyph, correcting the images using real pixel information, thus, improving image matching and 3-D reconstruction processes. In particular, the developed method employs deep learning architectures to classify image pixels to “noncaustics” and “caustics.” Then, it exploits the 3-D geometry of the scene to achieve a pixelwise correction, by transferring appropriate color values between the overlapping underwater images. Moreover, to fill the current gap, we have collected, annotated, and structured a real-world caustic data set, namely, R-CAUSTIC, which is openly available. Overall, based on the experimental results and validation, the developed methodology is quite promising in both detecting caustics and reconstructing their intensity.