archive
Every paper Pith has read. Search by title, abstract, or pith.
837 papers in eess.IV · page 9
-
Markerless cameras track heads at 2 mm accuracy for brain procedures
Markerless Head Tracking for Accurate and Accessible Neuronavigation
-
SOAR raises UAV LiDAR relocalization success by 40%
SOAR: Regression-based LiDAR Relocalization for UAVs
-
Asymmetric apertures enable guidestar-free real-time adaptive optics
Guidestar-Free Adaptive Optics with Asymmetric Apertures
-
Synthetic abundance maps train unsupervised hyperspectral sharpening
Synthetic Abundance Maps for Unsupervised Super-Resolution of Hyperspectral Remote Sensing Images
-
Joint deblurring-segmentation model sustains Dice on degraded endoscopic views
EndoCaver: Handling Fog, Blur and Glare in Endoscopic Images via Joint Deblurring-Segmentation
-
RGB wins k-means quantization in half of images
Optimized $k$-means color quantization of digital images in machine-based and human perception-based colorspaces
-
Diffraction similarity clusters 4D-STEM data into domains
Unsupervised segmentation and clustering workflow for efficient processing of 4D-STEM and 5D-STEM data
-
Synthetic abundances train super-resolution for real hyperspectral images
Unsupervised Super-Resolution of Hyperspectral Remote Sensing Images Using Fully Synthetic Training
-
Context-aware probing scales AI image quality checks to high resolutions
Q-Probe: Scaling Image Quality Assessment to High Resolution via Context-Aware Agentic Probing
-
Camera detections create full 360 LiDAR labels without annotations
XD-MAP: Cross-Modal Domain Adaptation via Semantic Parametric Maps for Scalable Training Data Generation
-
Large language models face a scaling wall from data scarcity
LLMOrbit: A Circular Taxonomy of Large Language Models -From Scaling Walls to Agentic AI Systems
-
Synthesis converts diffusion MRI alignment to standard unimodal registration
Bridging Modalities: Joint Synthesis and Registration Framework for Aligning Diffusion MRI with T1-Weighted Images
-
Fourier separation improves low-count PET reconstruction
FourierPET: Deep Fourier-based Unrolled Network for Low-count PET Reconstruction
-
DeTracker separates platform jitter from vehicle motion in satellite video
DeTracker: Motion-decoupled Vehicle Detection and Tracking in Unstabilized Satellite Videos
-
Self-supervised MRI risk equals weighted supervised risk
Towards a Unified Theoretical Framework for Splitting-based Self-Supervised MRI Reconstruction
-
LinMU matches VLM accuracy with linear complexity
LinMU: Multimodal Understanding Made Linear
-
Only 24% of fetal ultrasound AI studies report calibration
Uncertainty-Calibrated Explainable Artificial Intelligence for Fetal Ultrasound Plane Classification: A Systematic Review
-
Generalist model enables 24x faster heart MRI
Enabling Ultra-Fast Cardiovascular Imaging Across Heterogeneous Clinical Environments with A Generalist Foundation Model and Multimodal Database
-
Dual-stream transformer reaches 99.78% GI disease accuracy
A Graph-Augmented knowledge Distillation based Dual-Stream Vision Transformer with Region-Aware Attention for Gastrointestinal Disease Classification with Explainable AI
-
Soft brain regions enable cross-subject fMRI captioning
Unified Multimodal Brain Decoding via Cross-Subject Soft-ROI Fusion
-
AI models agree on lungs but produce invalid vertebrae in CT scans
In search of truth: Evaluating concordance of AI-based anatomy segmentation models
-
Dark-frame calibration closes 54-64% of noise gap in synthetic RAW images
SNIC: Synthesized Noisy Images using Calibration
-
Adaptable pipeline segments diverse brain tumors competitively
Adaptable Segmentation Pipeline for Diverse Brain Tumors with Radiomic-Guided Subtyping and Lesion-Wise Model Ensemble
-
LLM scripts automate CT incidental findings checks
INFORM-CT: INtegrating LLMs and VLMs FOR Incidental Findings Management in Abdominal CT
-
SynthPix streams synthetic PIV images on demand at accelerator speed
SynthPix: A lightspeed PIV image generator
-
Tumor-anchored random forest detects unsafe lung CT scans
Tumor-anchored deep feature random forests for out-of-distribution detection in lung cancer segmentation
-
Gating network fuses regional experts for Alzheimer's diagnosis
Interpretable Alzheimer's Diagnosis via Multimodal Fusion of Regional Brain Experts
-
Hybrid quantum model raises breast tumor classification accuracy
Parallel Multi-Circuit Quantum Feature Fusion in Hybrid Quantum-Classical Convolutional Neural Networks for Breast Tumor Classification
-
SAM 3 beats SAM 2 for most 3D medical segmentations
Comparing SAM 2 and SAM 3 for Zero-Shot Segmentation of 3D Medical Data
-
First DSLR stereo dataset varies focal length and aperture across real scenes
MODEST: Multi-Optics Depth-of-Field Stereo Dataset
-
Diffusion prior mainly warms up estimates near data manifold
DAPS++: Rethinking Diffusion Inverse Problems with Decoupled Posterior Annealing
-
Receiver protocol restores sender timing to smooth delivery
ARC: Consistent, Low-Latency Delivery via Receiver-Side Scheduling
-
Plug-in adapts foundation flow models for use as inverse problem priors
Saving Foundation Flow-Matching Priors for Inverse Problems
-
Cross-depth feature reuse cuts LiDAR bits at real-time speed
ELiC: Efficient LiDAR Geometry Compression via Cross-Bit-depth Feature Propagation and Bag-of-Encoders
-
Open Python tool generates brain perfusion maps with SSIM 0.8 to commercial standards
PyPeT: A Python Perfusion Tool for Automated Quantitative Brain CT and MR Perfusion Analysis
-
Noise combining slashes denoising steps in diffusion compression
Turbo-DDCM: Fast and Flexible Zero-Shot Diffusion-Based Image Compression
-
SPASHT boosts defect detection in fewer-view MPI SPECT
SPASHT: An image-enhancement method for sparse-view MPI SPECT
-
Spherical CNN separates crossing brain fibers at 0.32 ms per voxel
DeepFixel: Crossing white matter fiber identification through spherical convolutional neural networks
-
Multi-site MRI identifies 37 regions altered in TBI
Phenotype discovery of traumatic brain injury segmentations from heterogeneous multi-site data
-
Smooth contours match dense mask fidelity with far fewer parameters
Extremal Contours: Gradient-driven contours for compact visual attribution
-
Metrics perform equally on neural and traditional video codecs
Evaluating Video Quality Metrics for Neural and Traditional Codecs using 4K/UHD-1 Videos
-
Trajectory feedback refines 360-degree multi-object tracking
OmniTrack++: Omnidirectional Multi-Object Tracking by Learning Large-FoV Trajectory Feedback
-
By iteratively providing model information to updating networks
Towards robust quantitative photoacoustic tomography via learned iterative methods
-
MRI-tuned SAM improves small-structure accuracy by 42 percent
SAMRI: Segment Any MRI
-
Sound localization maps tool actions onto 3D surgical scenes
Sound Source Localization for Spatial Mapping of Surgical Actions in Dynamic Scenes
-
Multi-decoder model tops nuclei detection in three challenges
KongNet: A Multi-headed Deep Learning Model for Detection and Classification of Nuclei in Histopathology Images
-
Rotational symmetry helps limited-angle self-supervised CT reconstruction
Equivariance2Inverse: A Practical Self-Supervised CT Reconstruction Method Benchmarked on Real, Limited-Angle, and Blurred Data
-
Learnable noise blocks eavesdroppers in semantic image transmission
Privacy-Preserving Semantic Communication over Wiretap Channels with Learnable Differential Privacy
-
Refined data lifts ResNet hypoglycemia prediction by 2-3 percent
Benchmarking ResNet for Short-Term Hypoglycemia Classification with DiaData
-
Noise synthesis from a subspace solves inverse problems in diffusion models
Noise is All You Need: Solving Linear Inverse Problems by Noise Combination Sampling with Diffusion Models