arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2410.17064cs.CV
收藏

基于多核估计的目标分割

Multi Kernel Estimation based Object Segmentation

Haim Goldfisher, Asaf Yekutiel

AI总结:

本文提出Multi-KernelGAN,通过结合目标分割掩码估计多个核,并验证YOLOv8与SAM组合在超分辨率任务中优于传统单核方法。

摘要:

本文提出了一种通过增强KernelGAN算法实现多核估计的新方法,KernelGAN传统上为整幅图像估计单一核。我们引入了Multi-KernelGAN,它通过基于目标分割掩码估计两个不同的核来扩展KernelGAN的能力。我们的方法通过三种不同的途径进行验证:基于纹理的图像块快速傅里叶变换(FFT)计算、基于细节的分割,以及使用YOLOv8和Segment Anything Model(SAM)的基于深度学习的目标分割。在这些方法中,YOLO与SAM的组合在核估计上取得了最佳结果。实验结果表明,我们的多核估计技术在超分辨率任务中优于传统的单核方法。

英文摘要:

This paper presents a novel approach for multi-kernel estimation by enhancing the KernelGAN algorithm, which traditionally estimates a single kernel for the entire image. We introduce Multi-KernelGAN, which extends KernelGAN's capabilities by estimating two distinct kernels based on object segmentation masks. Our approach is validated through three distinct methods: texture-based patch Fast Fourier Transform (FFT) calculation, detail-based segmentation, and deep learning-based object segmentation using YOLOv8 and the Segment Anything Model (SAM). Among these methods, the combination of YOLO and SAM yields the best results for kernel estimation. Experimental results demonstrate that our multi-kernel estimation technique outperforms conventional single-kernel methods in super-resolution tasks.

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。

↑