A5079590055- Advanced Image Fusion Techniques
- Image Enhancement Techniques
- Advanced Image Processing Techniques
- Photoacoustic and Ultrasonic Imaging
- Image and Signal Denoising Methods
- Image Processing Techniques and Applications
- Advanced Vision and Imaging
- Remote-Sensing Image Classification
- Optical Coherence Tomography Applications
- Computer Graphics and Visualization Techniques
- Smart Agriculture and AI
- Plant Virus Research Studies
- 3D Shape Modeling and Analysis
- Insect-Plant Interactions and Control
- Model Reduction and Neural Networks
- Advanced X-ray and CT Imaging
- Medical Imaging Techniques and Applications
- Face and Expression Recognition
- Generative Adversarial Networks and Image Synthesis
- Digital Media Forensic Detection
- Anomaly Detection Techniques and Applications
University of Science and Technology of China
2022-2025
Chinese Academy of Sciences
2022-2024
Hefei Institutes of Physical Science
2022-2024
Institute of Intelligent Machines
2023-2024
Alibaba Group (United States)
2023
multimodal image fusion involves tasks like pan-sharpening and depth super-resolution. Both aim to generate high-resolution target images by fusing the complementary information from texture-rich guidance low-resolution counterparts. They are inborn with reconstructing high-frequency information. Despite their inherent frequency domain connection, most existing methods only operate solely in spatial rarely explore solutions domain. This study addresses this limitation proposing both domains....
Pan-sharpening aims to integrate the complementary information of texture-rich PAN images and multi-spectral (MS) produce MS images. Despite remarkable progress, existing state-of-the-art Pansharpening methods don't explicitly enforce learning between two modalities This leads redundancy not being handled well, which further limits performance these methods. To address above issue, we propose a novel mutual information-driven framework in this paper. be specific, first project image into...
Pansharpening aims to obtain high-resolution multispectral (MS) images for remote sensing systems and deep learning-based methods have achieved remarkable success. However, most existing are designed in a black-box principle, lacking sufficient interpretability. Additionally, they ignore the different characteristics of each band MS directly concatenate them with panchromatic (PAN) images, leading severe copy artifacts [9]. To address above issues, we propose an interpretable neural network,...
In this article, we propose a novel graph convolutional network (GCN) for pansharpening, defined as GCPNet, which consists of three main modules: the spatial GCN module (SGCN), spectral band (BGCN), and atrous pyramid (ASPM). Specifically, due to nature GCN, proposed SGCN BGCN are capable exploring long-range relationship between object global state in aspects, benefits pansharpened results has not been fully investigated before. addition, designed ASPM is equipped with multiscale...
Pan-sharpening aims to generate high-spatial resolution multi-spectral (MS) image by fusing panchromatic (PAN) and its corresponding low-spatial MS image. Despite the remarkable progress, most existing pan-sharpening methods only work in spatial domain rarely explore potential solutions frequency domain. In this paper, we propose a novel framework adaptively learning low-high information integration dual domains. It consists of three key designs: mask prediction sub-network, low-frequency...
The goal of pan-sharpening is to produce a high-spatial-resolution multi-spectral (HRMS) image from low-spatial-resolution (LRMS) counterpart by super-resolving the LRMS one under guidance texture-rich panchromatic (PAN) image. Existing research has concentrated on using spatial information generate HRMS images, but neglected investigate frequency domain, which severely restricts performance improvement. In this work, we propose novel approach, named Multi-Scale Dual-Domain Guidance Network...
Due to the physical hardware limits, multi-spectral (MS) images often suffer from low-spatial resolution, challenging their practical utility in real applications. Therefore, pan-sharpening technology has been widely explored as a popular tool generate with both high-spatial and high-spectral resolutions by integrating PAN MS images. In this paper, we propose an effective network, which consists of two core designs: PAN-guided band-aware feature enhancement module multi-focus fusion module....
In this paper, a novel virtual try-on algorithm, dubbed SAL-VTON, is proposed, which links the garment with person via semantically associated landmarks to alleviate misalignment. The are series of landmark pairs same local semantics on in-shop image and image. Based landmarks, SAL-VTON effectively models semantic association between person, making up for misalignment in overall deformation garment. outcome achieved three-stage framework: 1) estimated using localization model; 2) taking as...
Pan-sharpening is essentially a panchromatic (PAN)-guided super-resolution process, primarily focused on enhancing multi-spectral image quality. This methodology intricately incorporates the high-frequency derived from texture-rich PAN images into lower-resolution (LRMS) counterparts. However, current spatial domain techniques frequently face challenges in accurately restoring texture details, while frequency methods lack efficient interaction with domains, thus restricting overall model...
This report presents Wan, a comprehensive and open suite of video foundation models designed to push the boundaries generation. Built upon mainstream diffusion transformer paradigm, Wan achieves significant advancements in generative capabilities through series innovations, including our novel VAE, scalable pre-training strategies, large-scale data curation, automated evaluation metrics. These contributions collectively enhance model's performance versatility. Specifically, is characterized...
Pan-sharpening is essentially a panchromatic (PAN) image-guided low-spatial resolution MS image super-resolution problem. The commonly challenging issue of pan-sharpening how to correctly select consistent features and propagate them, properly handle inconsistent ones between PAN modalities. To solve this issue, we propose Normalization-based Feature Selection Restitution mechanism, which capable filtering out the promoting learn ones. Specifically, first modulate feature as style in space...
Pan-sharpening involves reconstructing missing high-frequency information in multi-spectral images with low spatial resolution, using a higher-resolution panchromatic image as guidance. Although the inborn connection frequency domain, existing pan-sharpening research has not almost investigated potential solution upon domain. To this end, we propose novel Frequency Adaptive Mixture of Experts (FAME) learning framework for pan-sharpening, which consists three key components: Separation...
Ensuring the efficient recognition and management of crop pests is crucial for maintaining balance in global agricultural ecosystems ecological harmony. Deep learning-based methods have shown promise pest recognition. However, prevailing often fail to address a critical issue: biased training dataset distribution stemming from tendency collect images primarily certain environmental contexts, such as paddy fields. This oversight hampers accuracy when encountering dissimilar samples,...
Pan-sharpening involves integrating information from lowresolution multi-spectral and high-resolution panchromatic images to generate counterparts. While recent advancements in the state space model, particularly efficient long-range dependency modeling achieved by Mamba, have revolutionized computer vision community, its untapped potential pan-sharpening motivates our exploration. Our contribution, Pan-Mamba, represents a novel pansharpening network that leverages efficiency of Mamba model...
Pan-sharpening, a panchromatic image guided low-spatial-resolution multi-spectral super-resolution task, aims to reconstruct the missing high-frequency information of high-resolution counterpart. Although inborn connection with frequency domain, existing pan-sharpening research has almost investigated potential solution upon thus limiting model performance improvement. To this end, we first revisit degradation process in Fourier space, and then devise Pyramid Dual Domain Injection Network...
RAW to sRGB mapping, which aims convert images from smartphones into RGB form equivalent that of Digital Single-Lens Reflex (DSLR) cameras, has become an important area research. However, current methods often ignore the difference between cell phone and DSLR camera images, a goes beyond color matrix extends spatial structure due resolution variations. Recent directly rebuild mapping via shared deep representation, limiting optimal performance. Inspired by Image Signal Processing (ISP)...
Pan-sharpening involves reconstructing missing high-frequency information in multi-spectral images with low spatial resolution, using a higher-resolution panchromatic image as guidance. Although the inborn connection frequency domain, existing pan-sharpening research has not almost investigated potential solution upon domain. To this end, we propose novel Frequency Adaptive Mixture of Experts (FAME) learning framework for pan-sharpening, which consists three key components: Separation...