A5101482554- Advanced Image Fusion Techniques
- Remote-Sensing Image Classification
- Image and Signal Denoising Methods
- Image Enhancement Techniques
- Seismic Imaging and Inversion Techniques
- Seismology and Earthquake Studies
- Medical Image Segmentation Techniques
- Advanced MIMO Systems Optimization
- Face and Expression Recognition
- Advanced Wireless Network Optimization
- Anomaly Detection Techniques and Applications
- Wireless Body Area Networks
- Cooperative Communication and Network Coding
Xi'an Jiaotong University
2023-2024
Xidian University
2023-2024
Multi-modality (MM) image fusion aims to render fused images that maintain the merits of different modalities, e.g., functional highlight and detailed textures. To tackle challenge in modeling cross-modality features decomposing desirable modality-specific modality-shared features, we propose a novel Correlation-Driven feature Decomposition Fusion (CDDFuse) network. Firstly, CDDFuse uses Restormer blocks extract shallow features. We then introduce dual-branch Transformer-CNN extractor with...
Multi-modality image fusion aims to combine different modalities produce fused images that retain the complementary features of each modality, such as functional highlights and texture details. To leverage strong generative priors address challenges unstable training lack interpretability for GAN-based methods, we propose a novel algorithm based on denoising diffusion probabilistic model (DDPM). The task is formulated conditional generation problem under DDPM sampling framework, which...
Image fusion is a significant problem in many fields including digital photography, computational imaging and remote sensing, to name but few. Recently, deep learning has emerged as an important tool for image fusion. This paper presents CSCFuse, which contains three convolutional sparse coding (CSC) networks kinds of tasks (i.e., infrared visible fusion, multi-exposure multi-spectral fusion). The CSC model the iterative shrinkage thresholding algorithm are generalized into dictionary...
First-break picking is a pivotal procedure in processing microseismic data for geophysics and resource exploration. Recent advancements deep learning have catalyzed the evolution of automated methods identifying first-break. Nevertheless, complexity seismic acquisition requirement detailed, expert-driven labeling often result outliers potential mislabeling within manually labeled datasets. These issues can negatively affect training neural networks, necessitating algorithms that handle or...
Multi-modal image fusion synthesizes information from multiple sources into a single image, facilitating downstream tasks such as semantic segmentation. Current approaches primarily focus on acquiring informative images at the visual display stratum through intricate mappings. Although some attempt to jointly optimize and tasks, these efforts often lack direct guidance or interaction, serving only assist with predefined loss. To address this, we propose an ``Unfolding Attribution Analysis...
Hyperspectral images (HSIs) are frequently noisy and of low resolution due to the constraints imaging devices. Recently launched satellites can concurrently acquire HSIs panchromatic (PAN) images, enabling restoration generate clean high-resolution imagery through fusing PAN for denoising super-resolution. However, previous studies treated these two tasks as independent processes, resulting in accumulated errors. This paper introduces \textbf{H}yperspectral \textbf{I}mage Joint...
The broadcasting nature of wireless signals may result in the task offloading process mobile edge computing (MEC) suffering serious information leakage. As a novel technology, physical layer security (PLS) combined with reconfigurable intelligent surfaces (RIS) can enhance transmission quality and security. This paper investigates MEC service delay problem RIS-aided vehicular networks under malicious eavesdropping. Due to lack an explicit formulation for optimization problem, we propose deep...