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.
7 day(s) with sentiment data
-
Rectified flows show promise for CT denoising without clean targets
Researchers have explored the use of unconditional rectified flows as a method for denoising low-dose CT scans without requiring clean training targets. Their findings suggest that a single step of the flow is optimal f…
-
New PRIN network enhances low-light images with perceptual and structural focus
Researchers have developed a new network called PRIN (Perceptual-Structural Retinex-Inspired Network) designed to enhance low-light images. This method decomposes images into reflectance and illumination components, app…
-
New PBSR method enhances single-image resolution using synthesized pseudo-burst frames
Researchers have developed a novel method called Pseudo-Burst Super-Resolution (PBSR) that enhances image resolution from a single input by synthesizing a pseudo-burst of frames. This technique utilizes zero-shot novel …
-
New ReMATF framework efficiently mitigates video turbulence
Researchers have developed ReMATF, a novel recurrent framework designed to mitigate atmospheric turbulence in videos. This lightweight system processes only two frames at a time, significantly reducing computational cos…
-
ParetoGS advances 3D Gaussian Splatting with continuous budget optimization
Researchers have introduced ParetoGS, a novel method for 3D Gaussian Splatting that optimizes scene representations for varying Gaussian counts. Unlike previous approaches that may require separate optimization for each…
-
ResGVC framework enhances generative video compression with residual coding
Researchers have introduced ResGVC, a novel framework for generative video compression that enhances fidelity by transmitting residual signals. This method guides denoising towards original images by encoding residual s…
-
Deep learning assesses road lane quality from dashcam video
Researchers have developed a new method for assessing road lane quality using deep learning and dashcam video. The system utilizes a geo-referenced dataset of over 63,000 frames collected in South Texas. It introduces t…
-
AI system SplatLab autonomously conducts 3DGS scientific research · 2 sources tracked
SplatLab, an autonomous AI research system, has been developed to conduct scientific discovery in the field of 3D Gaussian Splatting (3DGS). This system can autonomously reproduce published research, propose and impleme…
-
UniField++ framework enhances MRI image quality with loop reasoning
Researchers have developed UniField++, a novel two-agent framework designed to enhance MRI field-strength, aiming to combine the accessibility of low-field scanners with the image quality of high-field scanners. This fr…
-
New 3DGS method improves reconstruction quality using error-driven densification
Researchers have developed a new confidence-aware densification method for 3D Gaussian Splatting (3DGS) that improves reconstruction quality, particularly at lower primitive budgets. This approach prioritizes placing ne…
-
RetinaDiff improves retinal imaging with few-frame diffusion models
Researchers have developed RetinaDiff, a novel framework utilizing a conditional diffusion model to improve retinal laser speckle contrast imaging (LSCI). This method enhances motion robustness and requires only a few f…
-
New PolarScale benchmark targets radiometric scale in polarization imaging
Researchers have introduced PolarScale, a new benchmark designed to address the challenge of accurately estimating the radiometric scale in RGB-to-Stokes polarization imaging. Unlike previous methods that predict normal…
-
New BEMD-QBF method enhances CT image quality by reducing noise while preserving structure
Researchers have developed a novel framework called BEMD-QBF, which uses Bidimensional Empirical Mode Decomposition and Quaternion Bilateral Filtering to convert sharp-kernel CT images into a soft-kernel appearance. Thi…
-
New CT Image Denoising Framework Combines Decomposition and Curvelet Thresholding
Researchers have developed a novel hybrid denoising framework for CT images that combines multiple decomposition techniques like EMD, VMD, MEMD, and BEMD with curvelet transform thresholding. This method processes each …
-
New MAX framework enhances accelerated MRI reconstruction
Researchers have developed MAX (MAnifold eXpansion), a novel subject-specific framework designed to improve accelerated multi-contrast MRI reconstruction. MAX learns anatomical representations from a single fully sample…
-
SILSA framework enhances 3D generation with efficient slice latents · 2 sources tracked
Researchers have introduced SILSA, a novel framework for generating high-resolution 3D models that prioritizes topological consistency and efficiency. Unlike previous methods that fragment surfaces into numerous local t…
-
New FANVIDv2 benchmark evaluates video super-resolution for recognition tasks
Researchers have introduced FANVIDv2, a new benchmark designed to evaluate video super-resolution (VSR) models based on their effectiveness in recognition tasks, rather than traditional metrics like PSNR and SSIM. This …
-
GAN-generated sonar data realism questioned by task-aware evaluation
Researchers have investigated the effectiveness of Generative Adversarial Networks (GANs) in creating synthetic sonar data for robotic perception. They found that traditional image-fidelity metrics like SSIM and PSNR do…
-
New study evaluates mesh reconstruction methods for crop phenotyping
A new paper evaluates seven mesh reconstruction pipelines for their effectiveness in crop phenotyping, a process crucial for improving agricultural yield. The study found that the GGGS, PGSR, and 2DGS pipelines produced…
-
New Gaussian Encoding Method Reduces 3D Scientific Data Size
Researchers have developed a novel method for reducing the size of 3D field data, commonly used in scientific simulations. This approach utilizes a unified sample-based Gaussian encoding technique that can represent str…