Related papers: Using KL-Divergence to Focus Frequency Information…
Multi-source data classification is a critical yet challenging task for remote sensing image interpretation. Existing methods lack adaptability to diverse land cover types when modeling frequency domain features. To this end, we propose a…
High-dimensional images, known for their rich semantic information, are widely applied in remote sensing and other fields. The spatial information in these images reflects the object's texture features, while the spectral information…
Light field (LF) depth estimation plays a crucial role in many LF-based applications. Existing LF depth estimation methods consider depth estimation as a regression problem, where a pixel-wise L1 loss is employed to supervise the training…
Despite significant advancements of deep learning-based forgery detectors for distinguishing manipulated deepfake images, most detection approaches suffer from moderate to significant performance degradation with low-quality compressed…
Image restoration, which aims to recover high-quality images from their corrupted counterparts, often faces the challenge of being an ill-posed problem that allows multiple solutions for a single input. However, most deep learning based…
The rapid advancement of Generative Adversarial Networks (GANs) and diffusion models has enabled the creation of highly realistic synthetic images, presenting significant societal risks, such as misinformation and deception. As a result,…
While deep learning models like Vision Transformer (ViT) have achieved significant advances, they typically require large datasets. With data privacy regulations, access to many original datasets is restricted, especially medical images.…
This paper presents a novel and interpretable end-to-end learning framework, called the deep compensation unfolding network (DCUNet), for restoring light field (LF) images captured under low-light conditions. DCUNet is designed with a…
Light field (LF) image super-resolution (SR) is a challenging problem due to its inherent ill-posed nature, where a single low-resolution (LR) input LF image can correspond to multiple potential super-resolved outcomes. Despite this…
The malicious use and widespread dissemination of deepfake pose a significant crisis of trust. Current deepfake detection models can generally recognize forgery images by training on a large dataset. However, the accuracy of detection…
Due to the singularity of real-world paired datasets and the complexity of low-light environments, this leads to supervised methods lacking a degree of scene generalisation. Meanwhile, limited by poor lighting and content guidance, existing…
In this study, we reveal that the interaction between haze degradation and JPEG compression introduces complex joint loss effects, which significantly complicate image restoration. Existing dehazing models often neglect compression effects,…
In multimedia broadcasting, no-reference image quality assessment (NR-IQA) is used to indicate the user-perceived quality of experience (QoE) and to support intelligent data transmission while optimizing user experience. This paper proposes…
Purpose Medical imaging diagnosis faces challenges, including low-resolution images due to machine artifacts and patient movement. This paper presents the Frequency-Guided U-Net (GFNet), a novel approach for medical image segmentation that…
Maternal-fetal Ultrasound is the primary modality for monitoring fetal development, yet automated segmentation remains challenging due to the scarcity of high-quality annotations. To address this limitation, we propose a semi-supervised…
In surveillance, monitoring and tactical reconnaissance, gathering the right visual information from a dynamic environment and accurately processing such data are essential ingredients to making informed decisions which determines the…
Perceptual losses have emerged as powerful tools for training networks to enhance Low-Dose Computed Tomography (LDCT) images, offering an alternative to traditional pixel-wise losses such as Mean Squared Error, which often lead to…
With the rapid advancement of diffusion-based generative models, Stable Diffusion (SD) has emerged as a state-of-the-art framework for high-fidelity im-age synthesis. However, existing SD models suffer from suboptimal feature aggregation,…
Low-light images often suffer from severe noise, detail loss, and color distortion, which hinder downstream multimedia analysis and retrieval tasks. The degradation in low-light images is complex: luminance and chrominance are coupled,…
Image Representation learning via input reconstruction is a common technique in machine learning for generating representations that can be effectively utilized by arbitrary downstream tasks. A well-established approach is using…