HNN: Hierarchical Noise-Deinterlace Net Towards Image Denoising

In this paper, we propose a hierarchical framework for image denoising and term it Hierarchical Noise-Deinterlace Net (HNN). We propose a hierarchical framework to process both global and local information across distinct levels of hierarchy. More specifically, we propose a hierarchical encoder-decoder network, with a distinct Global-Local Spatio-Contextual (GLSC) block for learning of fine-grained features and high-frequency details in an image. The proposed framework improves image denoising, as it allows the model to capture and utilize information from different scales, ensuring a comprehensive understanding of the image content.
#PBVS #CVPR2024 #ComputerVisionResearch #ImageDenoising #cvpr