Marine Snow Removal Using Internally Generated Pseudo Ground Truth
This addresses the challenge of degraded underwater video quality for machine vision tasks, though it is incremental as it focuses on dataset generation rather than a new restoration method.
The paper tackles the problem of marine snow removal in underwater videos by proposing a framework to generate paired training datasets from raw footage, enabling supervised enhancement methods that improve image restoration without ground truth data.
Underwater videos often suffer from degraded quality due to light absorption, scattering, and various noise sources. Among these, marine snow, which is suspended organic particles appearing as bright spots or noise, significantly impacts machine vision tasks, particularly those involving feature matching. Existing methods for removing marine snow are ineffective due to the lack of paired training data. To address this challenge, this paper proposes a novel enhancement framework that introduces a new approach for generating paired datasets from raw underwater videos. The resulting dataset consists of paired images of generated snowy and snow, free underwater videos, enabling supervised training for video enhancement. We describe the dataset creation process, highlight its key characteristics, and demonstrate its effectiveness in enhancing underwater image restoration in the absence of ground truth.