通过自动生成伪真实数据，解决水下视频去海雪难题。
Marine Snow Removal Using Internally Generated Pseudo Ground Truth
- 从原始水下视频生成带海雪与无海雪的配对数据
- 在无真实标签情况下实现水下图像修复效果提升
- 适合从事水下视觉、海洋机器人研究者参考
水下视频常因光线吸收、散射及噪声源导致画质下降。其中，海雪（悬浮有机颗粒，表现为亮斑或噪声）严重影响机器视觉任务，尤其是特征匹配。现有去海雪方法因缺乏成对训练数据而效果不佳。本文提出一种新型增强框架，通过从原始水下视频中自动生成带海雪与无海雪的配对数据，构建可用于监督训练的图像对。该数据集包含生成的带雪与去雪视频对，显著提升了无真实标签条件下水下图像恢复的效果。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。