GitHub

Fully 1x1 Convolutional Network for Lightweight Image Super-Resolution

AIIA Lab, Harbin Institute of Technology. This repository is the official PyTorch implementation of "Fully 1×1 Convolutional Network for Lightweight Image Super-Resolution". If our work helps your ...
IEEE

Depth Map Super-Resolution via Deep Cross-Modality and Cross-Scale Guidance

Abstract: Guided depth super-resolution is essential in many applications, which enhances low-resolution (LR) depth maps using high-resolution (HR) RGB images from the same scene. However, the ...
GitHub

GitHub - BBillot/SynthSR: A framework for joint super-resolution and image synthesis, without requiring real training data

This repository contains an implementation of SynthSR, a convolutional neural network that turns a clinical MRI scan (or even CT scan!) of any orientation, resolution and contrast into 1 mm isotropic ...
Frontiers

Improved YOLOv8 method for photovoltaic panel surface state detection integrating spatial-to-depth convolution and Wise-IoU

The adopted split sizes and class-wise statistics are summarized in Table 1. To facilitate subsequent reproduction and comparative studies, the cleaned images, annotation files, and data-splitting ...