SAM-DiffSR: Structure-Modulated Diffusion Model for Image Super-Resolution
Diffusion-based super-resolution (SR) models have recently garnered significant attention
due to their potent restoration capabilities. But conventional diffusion models perform noise …
due to their potent restoration capabilities. But conventional diffusion models perform noise …
Super-resolution reconstruction of single image for latent features
Single-image super-resolution (SISR) typically focuses on restoring various degraded low-
resolution (LR) images to a single high-resolution (HR) image. However, during SISR tasks …
resolution (LR) images to a single high-resolution (HR) image. However, during SISR tasks …
PromptRR: Diffusion Models as Prompt Generators for Single Image Reflection Removal
Existing single image reflection removal (SIRR) methods using deep learning tend to miss
key low-frequency (LF) and high-frequency (HF) differences in images, affecting their …
key low-frequency (LF) and high-frequency (HF) differences in images, affecting their …
[HTML][HTML] Spatial Downscaling of Sea Surface Temperature Using Diffusion Model
S Wang, X Li, X Zhu, J Li, S Guo - Remote Sensing, 2024 - mdpi.com
In recent years, advancements in high-resolution digital twin platforms or artificial
intelligence marine forecasting have led to the increased requirements of high-resolution …
intelligence marine forecasting have led to the increased requirements of high-resolution …
[HTML][HTML] Adaptive Noise-Powered Diffusion Model for Efficient and Accurate Object Detection
X Zou, K Han, X Zhang, W Wang, N Wu - Applied Sciences, 2024 - mdpi.com
Recent advancements in object detection, particularly with DiffusionDet, have demonstrated
impressive performance. However, its reliance on numerous random noise-based object …
impressive performance. However, its reliance on numerous random noise-based object …
Multi-Branch Network for Color Image Denoising Using Dilated Convolution and Attention Mechanisms
MT Duong, BT Nguyen Thi, S Lee, MC Hong - Sensors, 2024 - mdpi.com
Image denoising is regarded as an ill-posed problem in computer vision tasks that removes
additive noise from imaging sensors. Recently, several convolution neural network-based …
additive noise from imaging sensors. Recently, several convolution neural network-based …
[HTML][HTML] Side-Scan Sonar Image Generator Based on Diffusion Models for Autonomous Underwater Vehicles
F Zhang, X Hou, Z Wang, C Cheng, T Tan - Journal of Marine Science …, 2024 - mdpi.com
In the field of underwater perception and detection, side-scan sonar (SSS) plays an
indispensable role. However, the imaging mechanism of SSS results in slow information …
indispensable role. However, the imaging mechanism of SSS results in slow information …
[HTML][HTML] Mitigating Adversarial Attacks in Object Detection through Conditional Diffusion Models
The field of object detection has witnessed significant advancements in recent years, thanks
to the remarkable progress in artificial intelligence and deep learning. These breakthroughs …
to the remarkable progress in artificial intelligence and deep learning. These breakthroughs …
[HTML][HTML] High-Precision Image Editing via Dual Attention Control in Diffusion Models Without Fine-Tuning
Z Pan, Y Kuang, J Lan, L Zhang - Applied Sciences, 2025 - mdpi.com
Existing diffusion models outperform generative models like Generative Adversarial
Networks in image synthesis and editing. However, they struggle with high-precision image …
Networks in image synthesis and editing. However, they struggle with high-precision image …
Human Body Restoration with One-Step Diffusion Model and A New Benchmark
J Gong, J Wang, Z Chen, X Liu, H Gu, Y Zhang… - arxiv preprint arxiv …, 2025 - arxiv.org
Human body restoration, as a specific application of image restoration, is widely applied in
practice and plays a vital role across diverse fields. However, thorough research remains …
practice and plays a vital role across diverse fields. However, thorough research remains …