IEEE

Towards Lightweight Hyperspectral Image Super-Resolution with Depthwise Separable Dilated Convolutional Network

Abstract: Deep neural networks have demonstrated highly competitive performance in super-resolution (SR) for natural images by learning mappings from low-resolution (LR) to high-resolution (HR) images ...
IEEE

MHCMamba: Multiscale Hybrid Convolution Mamba Network for Hyperspectral and LiDAR Image Classification

Abstract: The volume of multisource remote sensing (RS) data has grown significantly, making the integration of such data a critical focus in Earth observation research. Although multisource data ...
Scientific Research Publishing

Geo-Refined Point Transformer: Coordinate-Aware Excitation and Positional Upsampling for 3D Scene Segmentation ()

The proposed Coordinate-Aware Feature Excitation (CAFE) module and Position-Aware Upsampling (Pos-Up) module both adhere to ...
Hosted on MSN

Is Radeon Super Resolution (RSR) worth using?

amd announced Radeon Super Resolution (RSR) back at CES, and it has finally arrived in the latest driver. It uses the same upscaling algorithm as fsr but it is applied at the driver level, meaning it ...