研究人员开发了 PGE-SAM，一个旨在提高 Segment Anything Model (SAM) 在处理图像质量下降（如噪声或模糊）时的性能的新框架。该系统使用提示引导来聚焦相关区域的特征增强，并结合多尺度特征来恢复丢失的细节。此外，研究人员还推出了 DM-Seg，一个用于退化医学图像交互式分割的基准数据集，并证明 PGE-SAM 实现了最先进的鲁棒性，且参数量远少于先前的方法。 AI
影响 提高了分割模型在真实世界、图像质量下降条件下的鲁棒性。
排序理由 该集群包含一篇详细介绍新模型和基准的研究论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.30477v1 Announce Type: new Abstract: Segment Anything Model (SAM) has revolutionized promptable image segmentation with strong zero-shot generalization. However, its performance degrades substantially under real-world imaging artifacts such as noise, blur, and compress…
Segment Anything Model (SAM) has revolutionized promptable image segmentation with strong zero-shot generalization. However, its performance degrades substantially under real-world imaging artifacts such as noise, blur, and compression. Existing methods restore features globally …