MariData: 海洋环境下的单步非配对图像翻译
MariData: One-Step Unpaired Image Translation for Maritime Environments
AI总结：
针对海洋自主水面船舶训练数据稀缺问题，提出基于CycleGAN-turbo的单步非配对图像翻译框架，通过零卷积跳跃连接保留小目标细节，生成逼真的天气与光照条件合成数据。
摘要：
海洋自主水面船舶（MASS）鲁棒感知系统的发展受到多样化训练数据稀缺的严重制约，尤其是恶劣天气和低光照条件。由于在动态海洋环境中收集配对图像在物理上不可行，通过非配对图像到图像翻译生成合成数据提供了一种关键解决方案。然而，现有生成模型因潜在压缩瓶颈而无法保留小型导航目标的精细结构细节。在本文中，我们介绍了一个使用CycleGAN-turbo（一种单步非配对翻译架构）生成合成海洋数据的框架。通过引入零卷积跳跃连接以绕过变分自编码器（VAE）瓶颈，我们的方法在翻译过程中明确保留了小目标细节（例如远处的船只和海上标志）。我们收集了一个包含7000张海洋图像的数据集，用于训练和评估白天到雾天、白天到日落以及白天到夜晚的域翻译模型。定性评估和变强度推理研究表明，我们的方法有效地合成了逼真的大气条件，同时保持了场景的底层语义结构。白天到雾天和白天到日落模型表现出良好的结构保留，而白天到夜晚模型则突显了语义幻觉的挑战，例如由不平衡训练分布引起的人工海岸灯光生成。最终，这项工作建立了一个高效、结构感知的数据合成管道，直接解决了自主海洋导航中的数据稀缺瓶颈。
英文摘要：
The development on robust perception systems for Maritime Autonomous Surface Ships (MASS) is heavily constrained by the scarcity of diverse training data, particularly for adverse weather and low-light conditions. Because collecting paired images in dynamic maritime environments is physically impossible, synthetic data generation via unpaired image-to-image translation offers a critical solution. However, existing generative models suffer from failing to preserve the fine structural details of small navigational objects due to latent compression bottlenecks. In this paper, we introduce a framework for generating synthetic maritime data using CycleGAN-turbo, a one-step unpaired translation architecture. By incorporating zero-convolution skip connections to bypass the Variational Autoencoder (VAE) bottleneck, our approach explicitly preserves small object details (e.g., distant vessels and sea marks) during translation. We compiled a dataset of 7,000 maritime images to train and evaluate models for Day-to-Foggy, Day-to-Sunset, and Day-to-Night domain translations. Qualitative evaluations and variable-strength inference studies demonstrate that our method effectively synthesizes realistic atmospheric conditions while maintaining the underlying semantic structure of the scene. The Day-to-Foggy and Day-to-Sunset models exhibit great structural retention, whereas the Day-to-Night model highlights the challenge of semantic hallucination, such as generating artificial coastal lights, induced by unbalanced training distributions. Ultimately, this work establishes an efficient, structure-aware data synthesis pipeline that directly addresses the data scarcity bottleneck in autonomous maritime navigation.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
