CycleDiff: Cycle Diffusion Models for Unpaired Image-to-image Translation [0.03%]
CycleDiff：用于无配对图像到图像转换的循环扩散模型
Shilong Zou,Yuhang Huang,Renjiao Yi et al.
Shilong Zou et al.
We introduce a diffusion-based cross-domain image translator in the absence of paired training data. Unlike GAN-based methods, our approach integrates diffusion models to learn the image translation process, allowing for more coverable mode...
Onur Keles,A Murat Tekalp
Onur Keles
Neural networks commonly employ the McCulloch-Pitts neuron model, which is a linear model followed by a point-wise non-linear activation. Various researchers have already advanced inherently non-linear neuron models, such as quadratic neuro...
Disentangle to Fuse: Towards Content Preservation and Cross-Modality Consistency for Multi-Modality Image Fusion [0.03%]
分离以融合：基于内容保存和跨模式一致性的多模态图像融合技术
Xinran Qin,Yuning Cui,Shangquan Sun et al.
Xinran Qin et al.
Multi-modal image fusion (MMIF) aims to integrate complementary information from heterogeneous sensor modalities. However, substantial cross-modality discrepancies hinder joint scene representation and lead to semantic degradation in the fu...
Principal Component Maximization: A Novel Method for SAR Image Recovery from Raw Data without System Parameters [0.03%]
一种新颖的SAR原始数据无参成像方法：主元极大化法
Huizhang Yang,Liyuan Chen,Shao-Shan Zuo et al.
Huizhang Yang et al.
Synthetic Aperture Radar (SAR) imaging relies on using focusing algorithms to transform raw measurement data into radar images. These algorithms require knowledge of SAR system parameters, such as wavelength, center slant range, fast time s...
Deep Learning based Joint Geometry and Attribute Up-sampling for Large-Scale Colored Point Clouds [0.03%]
基于深度学习的大规模彩色点云联合几何和属性上采样技术
Yun Zhang,Feifan Chen,Na Li et al.
Yun Zhang et al.
Colored point cloud comprising geometry and attribute components is one of the mainstream representations enabling realistic and immersive 3D applications. To generate large-scale and denser colored point clouds, we propose a deep learning-...
SACMark: Spatial-Angle Consistency Watermarking Network for Light Field Image Copyright Protection [0.03%]
基于空间角度一致性的计算全栈标记方法LF图像版权保护Spatial-Angle Consistency水印网络LF图像版权保护
Junfeng Guo,Hui Wang,Shouxin Liu et al.
Junfeng Guo et al.
Light Field (LF) images provide rich visual representations of 3D scenes by capturing both spatial and angular information of light rays. However, their high dimensions present substantial challenges for conventional 2D image watermarking t...
Broadcast-Gated Attention with Identity Adaptive Integration for Efficient Image Super-Resolution [0.03%]
具有自适应身份集成的广播门控注意机制在高效图像超分辨率中的应用
Qian Wang,Yanyu Mao,Ruilong Guo et al.
Qian Wang et al.
Efficient image super-resolution (SR) models are essential for achieving high-quality image reconstruction with reduced computational complexity, particularly in resource-constrained environments. In this paper, we introduce a novel self-at...
IHDCP: Single Image Dehazing Using Inverted Haze Density Correction Prior [0.03%]
基于逆向霾密度矫正先验的单图去雾方法
Yun Liu,Tao Li,Chunping Tan et al.
Yun Liu et al.
Image dehazing, a crucial task in low-level vision, supports numerous practical applications, such as autonomous driving, remote sensing, and surveillance. This paper proposes IHDCP, a novel Inverted Haze Density Correction Prior for effici...
Equivariant High-Resolution Hyperspectral Imaging via Mosaiced and PAN Image Fusion [0.03%]
基于多光谱图像和全色图像融合的等变高空间分辨率高光谱成像
Nan Wang,Anjing Guo,Renwei Dian et al.
Nan Wang et al.
Existing mosaic-based snapshot hyperspectral imaging systems struggle to capture high resolution (HR) hyperspectral image (HSI), limiting its application. Fusing a low resolution (LR) mosaiced image with an HR panchromatic (PAN) image serve...
Individual & Common Attack: Enhancing Transferability in VLP Models through Modal Feature Exploitation [0.03%]
个体与共性攻击：通过模态特征利用提升VLP模型的迁移性
Yaguan Qian,Yaxin Kong,Qiqi Bao et al.
Yaguan Qian et al.
Vision-Language Pretrained (VLP) models exhibit strong multimodal understanding and reasoning capabilities, finding wide application in tasks such as image-text retrieval and visual grounding. However, they remain highly vulnerable to adver...