Smpconv: Self-moving point representations for continuous convolution
Continuous convolution has recently gained prominence due to its ability to handle
irregularly sampled data and model long-term dependency. Also, the promising …
irregularly sampled data and model long-term dependency. Also, the promising …
Gfcnet: contrastive learning network with geography feature space joint negative sample correction for land cover classification
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 …
images, the self-supervised contrastive learning paradigm driven by a large amount of …
Neural field convolutions by repeated differentiation
Neural fields are evolving towards a general-purpose continuous representation for visual
computing. Yet, despite their numerous appealing properties, they are hardly amenable to …
computing. Yet, despite their numerous appealing properties, they are hardly amenable to …
Neighborhood evaluator for efficient super-resolution reconstruction of 2D medical images
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 …
resolution (LR) images into high-fidelity high-resolution (HR) images by learning the low …
Neural Fields with Thermal Activations for Arbitrary-Scale Super-Resolution
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 …
local neural fields to represent continuous signals that can be sampled at different rates …
Analytical Design of Gaussian Anisotropic 2D FIR Filters and Their Implementation Using the Block Filtering Approach
R Matei, DF Chiper - Electronics, 2024 - mdpi.com
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 …
anisotropic Gaussian FIR filters. The design is achieved in the frequency domain and starts …