Bridging the turbidity gap with synthetic data

Abstract In recent years, the underwater image formation model has been widely used to generate synthetic underwater data. Although many approaches focus on scenes primarily affected by discoloration, they often overlook the model’s ability to capture the complex, distance-dependent structural degradations present in highly turbid environments. This paper extends our previous work, published in the 2025 International Conference on Computer Vision (ICCV) workshop proceedings, in which we introduced STSR , an improved synthetic data generation pipeline that includes the commonly omitted forward-scattering term and accounts for a nonuniform medium. In this journal version, we significantly expand on the original study by providing a more thorough description of the methodology and implementation details, as well as an extensive quantitative evaluation of the resulting synthetic data. We find that images generated with STSR result in improved generalization ability across models and turbidity levels. Data and code can be accessed through the project page: https://vap.aau.dk/sea-ing-through-scattered-rays .