CVAISep 18, 2025

Sea-ing Through Scattered Rays: Revisiting the Image Formation Model for Realistic Underwater Image Generation

arXiv:2509.15011v2h-index: 522025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)
Originality Incremental advance
AI Analysis

This work addresses the need for better synthetic data for underwater computer vision applications, but it is incremental as it builds on existing models with specific enhancements.

The authors tackled the problem of generating realistic synthetic underwater images, especially in turbid environments, by improving the image formation model to include forward scattering and nonuniform medium effects, resulting in qualitative improvements with a 82.5% selection rate in surveys.

In recent years, the underwater image formation model has found extensive use in the generation of 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 visibility loss present in highly turbid environments. In this work, we propose an improved synthetic data generation pipeline that includes the commonly omitted forward scattering term, while also considering a nonuniform medium. Additionally, we collected the BUCKET dataset under controlled turbidity conditions to acquire real turbid footage with the corresponding reference images. Our results demonstrate qualitative improvements over the reference model, particularly under increasing turbidity, with a selection rate of 82.5% by survey participants. Data and code can be accessed on the project page: vap.aau.dk/sea-ing-through-scattered-rays.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes