New Scientist

Quantum computers could help sharpen images of exoplanets

Combining two kinds of quantum computing devices could be just the trick for taking better images of faint, faraway ...
Comics Gaming Magazine on MSN

CES 2026: DLSS 4.5 brings cleaner upscaling and smarter frame generation to RTX GPUs

Last year at CES, NVIDIA introduced its RTX 50-series GPUs and DLSS 4, offering an early look at what was possible with multi ...
IEEE

Image Semantic Segmentation Algorithm Based on U-Net

Abstract: The U-Net algorithm, with its unique network structure and excellent performance, has become a classic algorithm in the field of image semantic segmentation. However, there are still some ...
IEEE

An Omnidirectional Image Blind Super-Resolution Algorithm Based on Random Degradation Mechanism

Abstract: Omnidirectional images (ODIs) are vital in VR and 360° imaging but suffer from quality degradation during acquisition and transmission. Existing blind SR methods often ignore ...
IEEE

Semantic-Driven Global-Local Fusion Transformer for Image Super-Resolution

Abstract: Image Super-Resolution (SR) has seen remarkable progress with the emergence of transformer-based architectures. However, due to the high computational cost, many existing transformer-based ...
IEEE

DADSR: Degradation-Aware Diffusion Super-Resolution Model for Object-Level SAR Image

Abstract: Synthetic aperture radar (SAR) plays a vital role in remote sensing applications but suffers from coupled degradation problems, including resolution deterioration, speckle noise, and ...
IEEE

Research on Cross-Sensor Remote Sensing Image Super-Resolution Method Based on Diffusion Models

Abstract: In remote sensing image (RSI) super-resolution (SR), traditional deep learning methods have made remarkable progress. However, these methods struggle to handle the complex mapping between ...
IEEE

MCBL-UNet: A Hybrid Mamba-CNN Boundary Enhanced Light-weight UNet for Placenta Ultrasound Image Segmentation

Abstract: The shape and size of the placenta are closely related to fetal development in the second and third trimesters of pregnancy. Accurately segmenting the placental contour in ultrasound images ...
IEEE

Research on ice thickness prediction of power transmission lines based on SO-CNN-LSTM algorithm

One of the fundamental requirements for the operation of power systems is safety and stability. However, in recent years, natural disasters such as rain, snow, and freezing weather have posed a ...
IEEE

Depthwise Convolution with Winograd Algorithm for Efficient CNN Acceleration

This work explores an efficient convolutional acceleration framework tailored for edge devices by integrating Depthwise Convolution with the Winograd algorithm. Through RTL-based hardware ...
IEEE

Research on visual image processing based on YOLO algorithm

Abstract: In the post-epidemic era, the manufacturing industry has undergone profound changes, and the importance of industrial machine vision technology has become increasingly prominent. In the face ...
IEEE

Single Image Super-Resolution Through Image Pixel Information Clustering and Generative Adversarial Network

Abstract: Recent advances in Super-Resolution (SR) image reconstruction using Convolutional Neural Networks (CNNs) have encountered significant challenges in effectively modeling the complex mapping ...