arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2503.12781cs.CVcs.AI
收藏

用于图像和视频分割的 SAM2:一项全面综述

SAM2 for Image and Video Segmentation: A Comprehensive Survey

School of Software engineering, Sichuan University(四川大学软件学院);School of Computer Science, Peking University(北京大学计算机学院)

Zhang Jiaxing, Tang Hao

AI总结:

该综述基于200多篇论文系统梳理SAM2在图像与视频分割中的技术特征、领域应用、跨域挑战及未来方向。

摘要:

尽管深度学习在图像和视频分割方面取得了显著进展,但现有模型在跨领域适应性和泛化能力方面仍面临挑战。图像和视频分割是计算机视觉中的基础任务,在医疗保健、农业、工业检测和自动驾驶等领域具有广泛应用。随着大规模基础模型的出现,SAM2——SAM(Segment Anything Model,分割一切模型)的改进版本——已针对分割任务进行了优化,并在复杂场景中展现出更强的性能。然而,SAM2 在特定领域中的适应性和局限性仍需进一步研究。本文系统分析了 SAM2 在图像和视频分割中的应用,并评估了其在各个领域中的性能。我们首先介绍图像分割的基础概念,对基础模型进行分类,并探讨 SAM 与 SAM2 的技术特征。随后,我们深入研究 SAM2 在静态图像和视频分割中的应用,重点强调其在医学影像等专业领域的性能以及跨领域适应性所面临的挑战。作为研究的一部分,我们综述了 200 多篇相关论文,以对该主题进行全面分析。最后,本文强调了 SAM2 在分割任务中的优势与不足,指出了其面临的技术挑战,并提出了未来发展方向。本综述为在真实场景中优化和应用 SAM2 提供了有价值的见解和实用建议。

英文摘要:

Despite significant advances in deep learning for image and video segmentation, existing models continue to face challenges in cross-domain adaptability and generalization. Image and video segmentation are fundamental tasks in computer vision with wide-ranging applications in healthcare, agriculture, industrial inspection, and autonomous driving. With the advent of large-scale foundation models, SAM2 - an improved version of SAM (Segment Anything Model)has been optimized for segmentation tasks, demonstrating enhanced performance in complex scenarios. However, SAM2's adaptability and limitations in specific domains require further investigation. This paper systematically analyzes the application of SAM2 in image and video segmentation and evaluates its performance in various fields. We begin by introducing the foundational concepts of image segmentation, categorizing foundation models, and exploring the technical characteristics of SAM and SAM2. Subsequently, we delve into SAM2's applications in static image and video segmentation, emphasizing its performance in specialized areas such as medical imaging and the challenges of cross-domain adaptability. As part of our research, we reviewed over 200 related papers to provide a comprehensive analysis of the topic. Finally, the paper highlights the strengths and weaknesses of SAM2 in segmentation tasks, identifies the technical challenges it faces, and proposes future development directions. This review provides valuable insights and practical recommendations for optimizing and applying SAM2 in real-world scenarios.

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。

↑