Multi Kernel Estimation based Object Segmentation
This work addresses a specific technical bottleneck in image super-resolution for computer vision applications, representing an incremental improvement over existing kernel estimation methods.
The paper tackles the problem of single-kernel estimation limitations in image super-resolution by proposing Multi-KernelGAN, which estimates two distinct kernels using object segmentation masks. Experimental results show this approach outperforms conventional single-kernel methods in super-resolution tasks.
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.