Real-World Underwater Enhancement: Challenges, Benchmarks, and Solutions Under Natural Light

TLDR

Underwater image enhancement is a critical low‑level vision task with many applications, prompting numerous algorithmic approaches that succeed under varied assumptions, datasets, and metrics, and often serve as preprocessing for higher‑level vision tasks. This study establishes an undersea imaging system and builds the large‑scale Real‑world Underwater Image Enhancement (RUIE) dataset, partitioned into three subsets. The dataset’s three subsets target visibility quality, color casts, and detection/classification, and the authors perform systematic experiments on RUIE to assess algorithmic performance, using object‑detection accuracy on enhanced images as a novel task‑specific metric. The evaluations confirm prevailing beliefs while revealing promising solutions and new directions for visibility enhancement, color correction, and object detection on real‑world underwater images, and the benchmark is publicly available at the provided GitHub repository.

Abstract

Underwater image enhancement is such an important low-level vision task with many applications that numerous algorithms have been proposed in recent years. These algorithms developed upon various assumptions demonstrate successes from various aspects using different data sets and different metrics. In this work, we setup an undersea image capturing system, and construct a large-scale Real-world Underwater Image Enhancement (RUIE) data set divided into three subsets. The three subsets target at three challenging aspects for enhancement, i.e., image visibility quality, color casts, and higher-level detection/classification, respectively. We conduct extensive and systematic experiments on RUIE to evaluate the effectiveness and limitations of various algorithms to enhance visibility and correct color casts on images with hierarchical categories of degradation. Moreover, underwater image enhancement in practice usually serves as a preprocessing step for mid-level and high-level vision tasks. We thus exploit the object detection performance on enhanced images as a brand new task-specific evaluation criterion. The findings from these evaluations not only confirm what is commonly believed, but also suggest promising solutions and new directions for visibility enhancement, color correction, and object detection on real-world underwater images. The benchmark is available at: https://github.com/dlut-dimt/Realworld-Underwater-Image-Enhancement-RUIE-Benchmark.