peak signal-to-noise ratio
PulseAugur coverage of peak signal-to-noise ratio — every cluster mentioning peak signal-to-noise ratio across labs, papers, and developer communities, ranked by signal.
10 day(s) with sentiment data
-
Vision Transformer and FFT-ReLU integrated for enhanced image deblurring
Researchers have developed a novel dual-domain architecture for image deblurring that integrates Vision Transformers (ViTs) with a frequency-domain FFT-ReLU module. This approach aims to enhance the recovery of sharp im…
-
SHFormer enhances MRI reconstruction with dynamic spectral filtering and transformers
Researchers have developed SHFormer, a novel neural network architecture designed for adaptive magnetic resonance imaging (MRI) reconstruction. This model utilizes a dynamic spectral filtering convolutional neural netwo…
-
New CLAHE pipeline enhances retinal images for improved diagnosis
Researchers have developed a novel two-stage image enhancement pipeline for retinal fundus images, combining luminosity correction with Contrast Limited Adaptive Histogram Equalization (CLAHE). This method specifically …
-
New pyMEAL toolbox enhances medical image translation robustness
Researchers have developed pyMEAL, a novel toolbox for medical image translation that addresses challenges like patient variability and limited training data. The system employs Multi-Encoder Augmentation-Aware Learning…
-
New framework analyzes CT reconstruction, noise impacts strategy
Researchers have developed a unified framework to analyze design choices in self-supervised sparse-view CT reconstruction. Their experiments on simulated and real-world datasets indicate that the optimal partitioning st…
-
FlowPET framework enhances low-count PET reconstruction with physics-informed approach
Researchers have developed FlowPET, a novel physics-informed framework for Positron Emission Tomography (PET) reconstruction, specifically designed to address challenges in low-count scenarios. Unlike traditional genera…
-
Simon-SR framework enhances image super-resolution with prompt-guided adaptation
Researchers have introduced Simon-SR, a novel multi-modal framework designed to enhance single-image super-resolution (SISR) by leveraging learnable prompts for semantic mining and text-image fusion. This approach aims …
-
New Vision Transformer Synthesizes Contrast-Enhanced Brain MRIs
Researchers have developed AA-ViT, an anatomically aware vision transformer designed to synthesize contrast-enhanced brain MRI scans from pre-contrast images. This method aims to improve tumor localization and diagnosis…
-
Diffusion model enhances face recognition from low-quality surveillance images
Researchers have developed FASR++, a new diffusion model designed to improve face recognition accuracy from low-quality surveillance images. This model aggregates features from multiple low-resolution images to generate…
-
New frameworks enhance MRI quality using physics-aware and unified approaches · 4 sources tracked
Researchers have developed two novel frameworks for enhancing Magnetic Resonance Imaging (MRI) quality. PhyMRI-SR approaches MRI super-resolution by treating it as a physics-aware reconstruction problem, adapting 2D Gau…
-
WorldSample framework boosts real-robot RL with synthetic data
Researchers have developed WorldSample, a framework designed to improve reinforcement learning (RL) for real-world robots. This system creates a closed loop between physical robot interactions and a generated world mode…
-
New metric links image dehazing to maritime visibility for safer navigation
Researchers have developed a new metric for evaluating image dehazing techniques, specifically for maritime surveillance. This metric aims to bridge the gap between image restoration quality and practical visibility est…
-
Log-Domain Noisier2Inverse framework advances ICF image denoising
A new self-supervised denoising framework, Log-Domain Noisier2Inverse, has been developed and evaluated for inertial confinement fusion (ICF) images affected by multiplicative uniform noise. The framework demonstrates s…
-
New research offers advanced methods for image denoising
Two new research papers propose novel methods for image denoising. The first paper introduces a Mixed-norm TV (MixTV) model that aims to reduce noise while preserving image edges, demonstrating improved effectiveness ov…
-
New method boosts neural video codec generalization
Researchers have developed a novel Training-Free Scale-Driven Online Flow Refinement (SOFR) method to enhance the generalization capabilities of neural video codecs (NVCs). This plug-and-play module integrates motion in…
-
Quantization: Key Technique for Efficient LLM Deployment
Quantization is a vital technique for deploying large language models (LLMs) efficiently by converting their weights and activations from floating-point to lower-precision integer formats. This process reduces memory fo…
-
NTIRE challenges push image super-resolution boundaries
The NTIRE 2024 and 2025 challenges on image super-resolution focused on enhancing low-resolution images by a factor of four. The 2024 challenge, with 20 teams submitting entries, primarily used PSNR for evaluation on th…
-
NTIRE 2026 Challenge benchmarks advanced image denoising techniques
The NTIRE 2026 Challenge on Image Denoising focused on restoring images degraded by high levels of additive white Gaussian noise. The competition evaluated advanced neural network architectures, prioritizing peak quanti…
-
AI improves MR reconstruction generalization for neonatal imaging
Researchers have developed new methods to improve the generalization of deep learning models for MR reconstruction, specifically for adult-to-neonatal brain imaging. By employing contrast-informed data augmentation and …
-
MetaRanker framework improves metalens image quality assessment
Researchers have developed MetaRanker, a novel human-in-the-loop framework designed to more accurately assess image quality for metalenses. Unlike traditional methods that rely on distortion-based metrics like PSNR, Met…