通过多核估计提升图像超分辨率，效果优于传统单核方法。
Multi Kernel Estimation based Object Segmentation
- 基于分割掩码分别估计多个核，突破单核全局适用限制。
- 结合YOLOv8与SAM的深度分割方案，实现最优核估计效果。
- 适用于需要精细纹理重建的高精度图像恢复任务。
本文提出一种基于多核估计的新方法，通过改进传统的KernelGAN算法（原仅对整图估计单一核）来实现更优的图像超分辨率。我们引入Multi-KernelGAN，根据对象分割掩码分别估计两个不同核。通过三种方式验证：基于纹理的块快速傅里叶变换（FFT）计算、基于细节的分割，以及基于YOLOv8和Segment Anything Model（SAM）的深度学习分割。实验表明，使用YOLO与SAM组合的方案在核估计上表现最佳。多核估计方法在超分辨率任务中显著优于传统单核方法。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。