AUTV：创建具有逐像素标注的水下视频数据集
AUTV: Creating Underwater Video Datasets with Pixel-wise Annotations
AI总结：
针对水下视频生成中的运动中断与错位问题，提出 AUTV 框架，构建带逐像素标注的真实与合成数据集 UTV、SUTV，并验证其可提升视频修复和对象分割等下游任务。
摘要：
水下视频分析受到动态海洋环境和相机运动的阻碍，仍是计算机视觉中的一项挑战性任务。现有的无需训练的视频生成技术以逐帧方式学习运动动力学，往往产生较差的结果，并伴有明显的运动中断和错位。为解决这些问题，我们提出了 AUTV，这是一个用于合成具有逐像素标注的海洋视频数据的框架。我们通过构建两个视频数据集证明了该框架的有效性，即 UTV 和 SUTV：UTV 是一个包含 2,000 个视频-文本对的真实世界数据集，SUTV 是一个包含 10,000 个视频并带有海洋对象分割掩码的合成视频数据集。UTV 提供多样化的水下视频以及全面标注，包括外观、纹理、相机内参、光照和动物行为。SUTV 可用于改进水下下游任务，其在视频修复和视频对象分割中得到了验证。
英文摘要：
Underwater video analysis, hampered by the dynamic marine environment and camera motion, remains a challenging task in computer vision. Existing training-free video generation techniques, learning motion dynamics on the frame-by-frame basis, often produce poor results with noticeable motion interruptions and misaligments. To address these issues, we propose AUTV, a framework for synthesizing marine video data with pixel-wise annotations. We demonstrate the effectiveness of this framework by constructing two video datasets, namely UTV, a real-world dataset comprising 2,000 video-text pairs, and SUTV, a synthetic video dataset including 10,000 videos with segmentation masks for marine objects. UTV provides diverse underwater videos with comprehensive annotations including appearance, texture, camera intrinsics, lighting, and animal behavior. SUTV can be used to improve underwater downstream tasks, which are demonstrated in video inpainting and video object segmentation.
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。
