Z Zhang, W Jing, H Li, C Tao, Y Zhang - Remote Sensing, 2023 - mdpi.com
With the continuous improvement in the volume and spatial resolution of remote sensing images, the self-supervised contrastive learning paradigm driven by a large amount of …
Neural fields are evolving towards a general-purpose continuous representation for visual computing. Yet, despite their numerous appealing properties, they are hardly amenable to …
Z Liu, J Han, J Liu, ZC Li, G Zhai - Computers in Biology and Medicine, 2024 - Elsevier
Background: Deep learning-based super-resolution (SR) algorithms aim to reconstruct low- resolution (LR) images into high-fidelity high-resolution (HR) images by learning the low …
Recent approaches for arbitrary-scale single image super-resolution (ASSR) have used local neural fields to represent continuous signals that can be sampled at different rates …
This work proposes an analytical design procedure for a particular class of 2D filters, namely anisotropic Gaussian FIR filters. The design is achieved in the frequency domain and starts …