Image enhancement
View article: Refining Visual Artifacts in Diffusion Models via Explainable AI-based Flaw Activation Maps
Refining Visual Artifacts in Diffusion Models via Explainable AI-based Flaw Activation Maps Open
Diffusion models have achieved remarkable success in image synthesis. However, addressing artifacts and unrealistic regions remains a critical challenge. We propose self-refining diffusion, a novel framework that enhances image generation …
View article: Simultaneous Enhancement and Noise Suppression under Complex Illumination Conditions
Simultaneous Enhancement and Noise Suppression under Complex Illumination Conditions Open
Under challenging light conditions, captured images often suffer from various degradations, leading to a decline in the performance of vision-based applications. Although numerous methods have been proposed to enhance image quality, they e…
View article: Simultaneous Enhancement and Noise Suppression under Complex Illumination Conditions
Simultaneous Enhancement and Noise Suppression under Complex Illumination Conditions Open
Under challenging light conditions, captured images often suffer from various degradations, leading to a decline in the performance of vision-based applications. Although numerous methods have been proposed to enhance image quality, they e…
View article: Refining Visual Artifacts in Diffusion Models via Explainable AI-based Flaw Activation Maps
Refining Visual Artifacts in Diffusion Models via Explainable AI-based Flaw Activation Maps Open
Diffusion models have achieved remarkable success in image synthesis. However, addressing artifacts and unrealistic regions remains a critical challenge. We propose self-refining diffusion, a novel framework that enhances image generation …
View article: See More, Change Less: Anatomy-Aware Diffusion for Contrast Enhancement
See More, Change Less: Anatomy-Aware Diffusion for Contrast Enhancement Open
Image enhancement improves visual quality and helps reveal details that are hard to see in the original image. In medical imaging, it can support clinical decision-making, but current models often over-edit. This can distort organs, create…
View article: See More, Change Less: Anatomy-Aware Diffusion for Contrast Enhancement
See More, Change Less: Anatomy-Aware Diffusion for Contrast Enhancement Open
Image enhancement improves visual quality and helps reveal details that are hard to see in the original image. In medical imaging, it can support clinical decision-making, but current models often over-edit. This can distort organs, create…
View article: DGGAN: Degradation Guided Generative Adversarial Network for Real-time Endoscopic Video Enhancement
DGGAN: Degradation Guided Generative Adversarial Network for Real-time Endoscopic Video Enhancement Open
Endoscopic surgery relies on intraoperative video, making image quality a decisive factor for surgical safety and efficacy. Yet, endoscopic videos are often degraded by uneven illumination, tissue scattering, occlusions, and motion blur, w…
View article: Brain MRI Images (Tumor and No Tumor)
Brain MRI Images (Tumor and No Tumor) Open
This dataset comprises primary clinical MRI scans acquired directly from the Department of Radiology at Dhaka Medical College Hospital (DMCH). It encompasses four diagnostic categories: Glioma, Meningioma, Pituitary, and No Tumor, represen…
View article: The role of AI in optimizing CMR image quality: A scoping review
The role of AI in optimizing CMR image quality: A scoping review Open
View article: DGGAN: Degradation Guided Generative Adversarial Network for Real-time Endoscopic Video Enhancement
DGGAN: Degradation Guided Generative Adversarial Network for Real-time Endoscopic Video Enhancement Open
Endoscopic surgery relies on intraoperative video, making image quality a decisive factor for surgical safety and efficacy. Yet, endoscopic videos are often degraded by uneven illumination, tissue scattering, occlusions, and motion blur, w…
View article: Brain MRI Images (Tumor and No Tumor)
Brain MRI Images (Tumor and No Tumor) Open
This dataset comprises primary clinical MRI scans acquired directly from the Department of Radiology at Dhaka Medical College Hospital (DMCH). It encompasses four diagnostic categories: Glioma, Meningioma, Pituitary, and No Tumor, represen…
View article: Low-Light Image Enhancement Based on Wavelet Local and Global Feature Fusion Network
Low-Light Image Enhancement Based on Wavelet Local and Global Feature Fusion Network Open
A wavelet-based local and global feature fusion network (LAGN) is proposed for low-light image enhancement, aiming to enhance image details and restore colors in dark areas. This study focuses on addressing three key issues in low-light im…
View article: Underwater image enhancement via adaptive color-cast elimination and multi-weight pyramid fusion
Underwater image enhancement via adaptive color-cast elimination and multi-weight pyramid fusion Open
View article: Structure-Aware Adaptive Kernel MPPCA Denoising for Diffusion MRI
Structure-Aware Adaptive Kernel MPPCA Denoising for Diffusion MRI Open
Diffusion-weighted MRI (DWI) at high b-values often suffers from low signal-to-noise ratio (SNR), making image quality poor. Marchenko-Pastur PCA (MPPCA) is a popular method to reduce noise, but it uses a fixed patch size across the whole …
View article: Structure-Aware Adaptive Kernel MPPCA Denoising for Diffusion MRI
Structure-Aware Adaptive Kernel MPPCA Denoising for Diffusion MRI Open
Diffusion-weighted MRI (DWI) at high b-values often suffers from low signal-to-noise ratio (SNR), making image quality poor. Marchenko-Pastur PCA (MPPCA) is a popular method to reduce noise, but it uses a fixed patch size across the whole …
View article: PixlMap can correctly classify cells without the need for whole cell expansion.
PixlMap can correctly classify cells without the need for whole cell expansion. Open
A. A mIF image of panel 2 in S1 Table showing only pan-cytokeratin (green) and DAPI (blue) (left), and PixlMap’s pan-cytokeratin probability heatmap from the mIF image (right). Scale bar = 50 µm. B. A nuclear detection APP wa…
View article: AI-based Image Enhancement and Optical Distortion Correction for 3D Integral Imaging and Display using Fermi-Level Pinning-Free and Low-Resistance Single-Pixel Imager
AI-based Image Enhancement and Optical Distortion Correction for 3D Integral Imaging and Display using Fermi-Level Pinning-Free and Low-Resistance Single-Pixel Imager Open
View article: AtiqEmenent/DCBD-AV1-ImageEnhancement: DCBD-AV1 Image Enhancement v1.0
AtiqEmenent/DCBD-AV1-ImageEnhancement: DCBD-AV1 Image Enhancement v1.0 Open
This repository contains a Google Coab file (.ipynb) that implements an image enhancement pipeline for AV1-based image processing. The notebook demonstrates how to improve image quality using advanced denoising and enhancement techniques.
View article: AtiqEmenent/DCBD-AV1-ImageEnhancement: DCBD-AV1 Image Enhancement v1.0
AtiqEmenent/DCBD-AV1-ImageEnhancement: DCBD-AV1 Image Enhancement v1.0 Open
This repository contains a Google Coab file (.ipynb) that implements an image enhancement pipeline for AV1-based image processing. The notebook demonstrates how to improve image quality using advanced denoising and enhancement techniques.
View article: GLUS: Guidance Loss Driven Plug-and-Play Diffusion for Ultrasound Image Super-Resolution
GLUS: Guidance Loss Driven Plug-and-Play Diffusion for Ultrasound Image Super-Resolution Open
This paper introduces GLUS, a novel training-free plugand-play framework for ultrasound (US) super-resolution. GLUS extends the residual plug-and-play paradigm by incorporating a tailored guidance energy function to capture the domain-spec…
View article: NightTrack: Joint Night-Time Image Enhancement and Object Tracking for UAVs
NightTrack: Joint Night-Time Image Enhancement and Object Tracking for UAVs Open
UAV-based visual object tracking has recently become a prominent research focus in computer vision. However, most existing trackers are primarily benchmarked under well-illuminated conditions, largely overlooking the challenges that may ar…
View article: TPCNet: Triple physical constraints for Low-light Image Enhancement
TPCNet: Triple physical constraints for Low-light Image Enhancement Open
Low-light image enhancement is an essential computer vision task to improve image contrast and to decrease the effects of color bias and noise. Many existing interpretable deep-learning algorithms exploit the Retinex theory as the basis of…
View article: TPCNet: Triple physical constraints for Low-light Image Enhancement
TPCNet: Triple physical constraints for Low-light Image Enhancement Open
Low-light image enhancement is an essential computer vision task to improve image contrast and to decrease the effects of color bias and noise. Many existing interpretable deep-learning algorithms exploit the Retinex theory as the basis of…
View article: A COMPARATIVE STUDY ALGORITHM FOR NOISY IMAGE RESTORATION IN THE FIELD OF MEDICAL IMAGING
A COMPARATIVE STUDY ALGORITHM FOR NOISY IMAGE RESTORATION IN THE FIELD OF MEDICAL IMAGING Open
This paper presents the performance analysis of different basic techniques used for the image restoration.Restoration is a process by removing blur and noise from image and get back the original form. Medicalimages play a vital role in dea…
View article: Person Re-Identification Enhanced by Super-Resolution Technology
Person Re-Identification Enhanced by Super-Resolution Technology Open
With rising demand for cross-camera person re-identification (ReID) in smart cities, low-resolution (LR) images severely hinder practical ReID performance due to detail loss and weakened identity features. This paper proposes two solutions…
View article: Ultrasonic testing data denoising and image enhancement method combined with fuzzy algorithm
Ultrasonic testing data denoising and image enhancement method combined with fuzzy algorithm Open
View article: Figure 4 from VCAM-1–targeted MRI Improves Detection of the Tumor-brain Interface
Figure 4 from VCAM-1–targeted MRI Improves Detection of the Tumor-brain Interface Open
Anti-VCAM-1–targeted MRI reveals tumor margins in U87MG brain tumors. A and B, Pre-/post-gadolinium T1-weighted images from rat brains with intrastriatal U87MG tumors. Matched pre-/post-MPIO T2
View article: Comparison of image quality in 40 keV virtual monoenergetic images of dual-energy CT pulmonary angiography using deep learning and iterative reconstruction algorithms under optimized low dose scanning protocols
Comparison of image quality in 40 keV virtual monoenergetic images of dual-energy CT pulmonary angiography using deep learning and iterative reconstruction algorithms under optimized low dose scanning protocols Open
View article: Imaging of Tissue and Cell Dynamics: introduction to the feature issue
Imaging of Tissue and Cell Dynamics: introduction to the feature issue Open
View article: VAOT: Vessel-Aware Optimal Transport for Retinal Fundus Enhancement
VAOT: Vessel-Aware Optimal Transport for Retinal Fundus Enhancement Open
Color fundus photography (CFP) is central to diagnosing and monitoring retinal disease, yet its acquisition variability (e.g., illumination changes) often degrades image quality, which motivates robust enhancement methods. Unpaired enhance…