Chenlu Hu — accepted AI-conference papers

2024

CROCFUN: Cross-Modal Conditional Fusion Network for Pansharpening

Mengting Ma, Chenlu Hu, Huanting Zhang, Xiaowen Ma, Tian Feng, Wei Zhang

ICASSP 2024accepted

Pansharpening aims to reconstruct a high-fidelity multispectral (HR-MS) image by fusing a multispectral (MS) image and a panchromatic (PAN) image. However, conventional pansharpening methods often struggle to address the modal gap between PAN and MS images. In this paper, we propose a novel cross-mo…

Cited by 0 Source ↗Scholar ↗

2023

Log-Can: Local-Global Class-Aware Network For Semantic Segmentation of Remote Sensing Images

Xiaowen Ma, Mengting Ma, Chenlu Hu, Zhiyuan Song, Ziyan Zhao, Tian Feng +1

ICASSP 2023accepted

Remote sensing images are known of having complex backgrounds, high intra-class variance and large variation of scales, which bring challenge to semantic segmentation. We present LoG-CAN, a multi-scale semantic segmentation network with a global class-aware (GCA) module and local class-aware (LCA) m…

Cited by 0 Source ↗Scholar ↗