![\"Underwater](\"https:\/\/scitechdaily.com\/images\/Underwater-Scene-With-Original-Photo-and-Color-Corrected-Version-1.jpg\")
<\/a>The colour-correcting software known as \u201cSeaSplat\u201d reveals underwater options in colours that seem extra true to life.<\/strong><\/p>\n The ocean is full of life, but a lot of it stays hidden except noticed at very shut vary. Water acts like a pure veil, bending and scattering gentle whereas additionally dimming it because it strikes via the dense medium and displays off numerous suspended particles. Due to this, precisely capturing the true colours of underwater objects is extraordinarily tough with out close-up imaging.<\/p>\n Researchers at MIT<\/span> and the Woods Hole Oceanographic Institution (WHOI) have created an image-analysis system that removes many of the ocean\u2019s optical distortions. The tool produces visuals of underwater scenes that appear as though the water has been removed, restoring their natural colors. To achieve this, the team combined the color-correction tool with a computational model that transforms images into a three-dimensional underwater \u201cworld\u201d that can be explored virtually.<\/p>\n The team named the tool \u201cSeaSplat,\u201d drawing inspiration from both its underwater focus and the technique of 3D Gaussian splatting (3DGS). This method stitches multiple images together to form a complete 3D representation of a scene, which can then be examined in detail from any viewpoint.<\/p>\n \u201cWith SeaSplat, it can model explicitly what the water is doing, and as a result, it can in some ways remove the water, and produces better 3D models of an underwater scene,\u201d says MIT graduate student Daniel Yang.<\/p>\n The researchers applied SeaSplat to images of the sea floor taken by divers and underwater vehicles, in various locations, including the U.S. Virgin Islands. The method generated 3D \u201cworlds\u201d from the images that were truer, more vivid, and varied in color, compared to previous methods.\u00a0<\/p>\n The researchers note that SeaSplat could become a valuable tool for marine biologists studying the condition of ocean ecosystems. For example, when an underwater robot surveys and photographs a coral reef, SeaSplat can process the images in real time and create a true-color, three-dimensional model. Scientists could then virtually \u201cfly\u201d through this digital environment at their own pace, examining it for details such as early signs of coral bleaching.<\/p>\n \u201cBleaching looks white from close up, but could appear blue and hazy from far away, and you might not be able to detect it,\u201d says Yogesh Girdhar, an associate scientist at WHOI. \u201cCoral bleaching, and different coral species<\/span>, could be easier to detect with SeaSplat imagery, to get the true colors in the ocean.\u201d\u00a0<\/p>\n Girdhar and Yang will present a\u00a0paper\u00a0detailing SeaSplat at the IEEE International Conference on Robotics and Automation (ICRA). Their study co-author is John Leonard, professor of mechanical engineering at MIT.<\/p>\n Light behaves differently in water than in air, altering both the appearance and clarity of objects. Over the past several years, scientists have tried to design color-correcting methods to recover the original appearance of underwater features. Many of these efforts adapted techniques originally developed for use on land, such as those used to restore clarity in foggy conditions. One notable example is the algorithm \u201cSea-Thru,\u201d which can reproduce realistic colors but requires enormous computing power, making it impractical for generating three-dimensional models of ocean scenes.<\/p>\n At the same time, researchers have advanced the technique of 3D Gaussian splatting, which allows images of a scene to be combined and filled in to create a seamless three-dimensional reconstruction. These models support \u201cnovel view synthesis,\u201d enabling viewers to explore a 3D scene not only from the original vantage points of the images but also from any other angle or distance.<\/p>\n But 3DGS has only successfully been applied to environments out of water. Efforts to adapt 3D reconstruction to underwater imagery have been hampered, mainly by two optical underwater effects: backscatter and attenuation. Backscatter occurs when light reflects off of tiny particles in the ocean, creating a veil-like haze. Attenuation is the phenomenon by which light of certain wavelengths attenuates, or fades with distance. In the ocean, for instance, red objects appear to fade more than blue objects when viewed from farther away.\u00a0<\/p>\n Out of water, the color of objects appears more or less the same regardless of the angle or distance from which they are viewed. In water, however, color can quickly change and fade depending on one\u2019s perspective. When 3DGS methods attempt to stitch underwater images into a cohesive 3D whole, they are unable to resolve objects due to aquatic backscatter and attenuation effects that distort the color of objects at different angles.\u00a0<\/p>\n \u201cOne dream of underwater robotic vision that we have is: Imagine if you could remove all the water in the ocean. What would you see?\u201d Leonard says.\u00a0<\/p>\n In their new work, Yang and his colleagues developed a color-correcting algorithm that accounts for the optical effects of backscatter and attenuation. The algorithm determines the degree to which every pixel in an image must have been distorted by backscatter and attenuation effects, and then essentially takes away those aquatic effects, and computes what the pixel\u2019s true color must be.\u00a0<\/p>\n Yang then worked the color-correcting algorithm into a 3D Gaussian splatting model to create SeaSplat, which can quickly analyze underwater images of a scene and generate a true-color, 3D virtual version of the same scene that can be explored in detail from any angle and distance.\u00a0<\/p>\n The team applied SeaSplat to multiple underwater scenes, including images taken in the Red Sea, in the Caribbean off the coast of Cura\u00e7ao, and the Pacific Ocean, near Panama. These images, which the team took from a pre-existing dataset, represent a range of ocean locations and water conditions. They also tested SeaSplat on images taken by a remote-controlled underwater robot in the U.S. Virgin Islands.\u00a0<\/p>\n From the images of each ocean scene, SeaSplat generated a true-color 3D world that the researchers were able to virtually explore, for instance, zooming in and out of a scene and viewing certain features from different perspectives. Even when viewing from different angles and distances, they found objects in every scene retained their true color, rather than fading as they would if viewed through the actual ocean.<\/p>\n \u201cOnce it generates a 3D model, a scientist can just \u2018swim\u2019 through the model as though they are scuba-diving, and look at things in high detail, with real color,\u201d Yang says.\u00a0<\/p>\n For now, the method requires hefty computing resources in the form of a desktop computer that would be too bulky to carry aboard an underwater robot. Still, SeaSplat could work for tethered operations, where a vehicle, tied to a ship, can explore and take images that can be sent up to a ship\u2019s computer.\u00a0<\/p>\n \u201cThis is the first approach that can very quickly build high-quality 3D models with accurate colors, underwater, and it can create them and render them fast,\u201d Girdhar says. \u201cThat will help to quantify biodiversity, and assess the health of coral reefs and other marine communities.\u201d<\/p>\n Reference: \u201cSeaSplat: Representing Underwater Scenes with 3D Gaussian Splatting and a Physically Grounded Image Formation Model\u201d by Daniel Yang, John J. Leonard and Yogesh Girdhar, 25 September 2024, arXiv. This work was supported, in part, by\u00a0the Investment in Science Fund at WHOI, and by the U.S. National Science Foundation.<\/p>\n Never miss a breakthrough: Join the SciTechDaily newsletter.<\/a><\/b><\/p>\n<\/p><\/div>\nCoral reefs and marine health<\/h4>\n
<\/a>Aquatic optics<\/h4>\n
Testing across oceans<\/h4>\n
DOI: 10.48550\/arXiv.2409.17345<\/a><\/p>\n