archive
Every paper Pith has read. Search by title, abstract, or pith.
837 papers in eess.IV · page 7
-
Metasurface camera does near and far imaging plus mm ranging in one shot
Compact single-shot ranging and near-far imaging using metasurfaces
-
Text priors boost stereo volume estimates
Not Your Stereo-Typical Estimator: Combining Vision and Language for Volume Perception
-
Stochastic gradient cuts memory for neural CT reconstruction
Memory-efficient optimization of implicit neural representations for CT reconstruction
-
Hybrid model reaches 100% accuracy on lung-colon and leukemia images
DSVTLA: Deep Swin Vision Transformer-Based Transfer Learning Architecture for Multi-Type Cancer Histopathological Cancer Image Classification
-
One-step diffusion generates chest X-ray reports 8x faster
ECHO: Efficient Chest X-ray Report Generation with One-step Block Diffusion
-
One-step diffusion produces accurate chest X-ray reports 8x faster
ECHO: Efficient Chest X-ray Report Generation with One-step Block Diffusion
-
Multi-task JRD model boosts VCM by 3.86% BD-mAP
Multi-task Just Recognizable Difference for Video Coding for Machines: Database, Model, and Coding Application
-
Clifford fusion enables real-time 4K low-light enhancement on one device
UHD Low-Light Image Enhancement via Real-Time Enhancement Methods with Clifford Information Fusion
-
Decoupled network restores multi-degraded UAV images
Compositional-Degradation UAV Image Restoration: Conditional Decoupled MoE Network and A Benchmark
-
Automated CT model forecasts recurrence in HPV throat cancer
AMO-ENE: Attention-based Multi-Omics Fusion Model for Outcome Prediction in Extra Nodal Extension and HPV-associated Oropharyngeal Cancer
-
GPU makes non-Fourier SENSE reconstruction practical on spiral data
A GPU-enhanced workflow for non-Fourier SENSE reconstruction
-
Commutator condition saves 33% compute on diffusion previews
Training-free, Perceptually Consistent Low-Resolution Previews with High-Resolution Image for Efficient Workflows of Diffusion Models
-
Frozen vision models locate image manipulations via a small adapter
Off-the-shelf Vision Models Benefit Image Manipulation Localization
-
Uncertainty routing improves medical image model calibration by 35%
MedFormer-UR: Uncertainty-Routed Transformer for Medical Image Classification
-
Training-free losses beat ANTs and DINO in multi-modal scans
Search-MIND: Training-Free Multi-Modal Medical Image Registration
-
Deep learning yields diagnostic heart MRI from two heartbeats
PSIRNet: Deep Learning-based Free-breathing Rapid Acquisition Late Enhancement Imaging
-
INR conditioning lifts perceptual quality at under 0.05 bpp
DiV-INR: Extreme Low-Bitrate Diffusion Video Compression with INR Conditioning
-
Diffusion transformer sharpens virtual IHC stains without artifacts
HistDiT: A Structure-Aware Latent Conditional Diffusion Model for High-Fidelity Virtual Staining in Histopathology
-
Loss tweaks stop deep image prior from overfitting on hyperspectral images
Preventing Overfitting in Deep Image Prior for Hyperspectral Image Denoising
-
Event-based odometry runs on 86 mW microcontrollers
TinyDEVO: Deep Event-based Visual Odometry on Ultra-low-power Multi-core Microcontrollers
-
HEVC ROI encryption reaches exact 8x8 coding-unit precision
A H.265/HEVC Fine-Grained ROI Video Encryption Algorithm Based on Coding Unit and Prompt Segmentation
-
Tiny network segments knee cartilage on handheld ultrasound
MonoUNet: A Robust Tiny Neural Network for Automated Knee Cartilage Segmentation on Point-of-Care Ultrasound Devices
-
Tiny model segments knee cartilage on portable ultrasound
MonoUNet: A Robust Tiny Neural Network for Automated Knee Cartilage Segmentation on Point-of-Care Ultrasound Devices
-
Diffusion restores encoder features for sharper depth maps
Monocular Depth Estimation From the Perspective of Feature Restoration: A Diffusion Enhanced Depth Restoration Approach
-
Metasurface telephoto reaches 0.44 ratio at 13 mm track length
MetaTele: Compact Refractive Metasurface Computational Telephoto Camera
-
Semantic masks from blurry faces sharpen deblurring in UNet
SMFD-UNet: Semantic Face Mask Is The Only Thing You Need To Deblur Faces
-
Optimal transport balances experts for slide-image classification
Region-Graph Optimal Transport Routing for Mixture-of-Experts Whole-Slide Image Classification
-
ESB halves transmission time and energy versus BLE for low-power IoT
Enhanced ShockBurst for Ultra Low-Power On-Demand Sensing
-
SurFITR dataset shows forgery detectors fail on surveillance scenes
SurFITR: A Dataset for Surveillance Image Forgery Detection and Localisation
-
Modeling inter-person links improves 2D-to-3D pose lifting in groups
MuPPet: Multi-person 2D-to-3D Pose Lifting
-
Pixel discriminator adapts GAN to clean photos for poster layouts
GAN-based Domain Adaptation for Image-aware Layout Generation in Advertising Poster Design
-
Local windows and continuity loss halve video model training cost
Accelerating Training of Autoregressive Video Generation Models via Local Optimization with Representation Continuity
-
Nine-camera system tracks 3D vessel motion in thrombectomy phantoms
4D Vessel Reconstruction for Benchtop Thrombectomy Analysis
-
LiftFormer lifts image features into depth subspaces for sharper maps
LiftFormer: Lifting and Frame Theory Based Monocular Depth Estimation Using Depth and Edge Oriented Subspace Representation
-
Matching quantization noise to diffusion noise raises compression fidelity
A Noise Constrained Diffusion (NC-Diffusion) Framework for High Fidelity Image Compression
-
Hybrid WarpRNN-grid model reaches 33.73 dB PSNR on UVG video
CWRNN-INVR: A Coupled WarpRNN based Implicit Neural Video Representation
-
Neural model recovers 4D spectra from 1/32 of samples
Accelerating 4D Hyperspectral Imaging through Physics-Informed Neural Representation and Adaptive Sampling
-
One PINN run ranks all sensors for inverse accuracy
FOSSA: First-Order Optimality-Based Sensor Selection for PINN Inverse Problems, with Application to Electrocardiographic Imaging
-
Dynamic privacy boosts accuracy in federated medical segmentation
ADP-FL-MedSeg: Adaptive Differential Privacy for Federated Medical Segmentation Across Diverse Modalities
-
Adaptive privacy matches non-private federated learning accuracy
ADP-FL-MedSeg: Adaptive Differential Privacy for Federated Medical Segmentation Across Diverse Modalities
-
Graph embeddings flag microservice anomalies missed by load tests
From Load Tests to Live Streams: Graph Embedding-Based Anomaly Detection in Microservice Architectures
-
Predicted eye movements improve LLM radiology reports
Gaze2Report: Radiology Report Generation via Visual-Gaze Prompt Tuning of LLMs
-
Paired food photos let vision models estimate exact consumption
DietDelta: A Vision-Language Approach for Dietary Assessment via Before-and-After Images
-
Adapted diffusion model cuts CT artifact training data to 16-128 pairs
Leveraging Image Editing Foundation Models for Data-Efficient CT Metal Artifact Reduction
-
Cinema SDR and HDR masters follow stable luminance mapping
Structural Regularities of Cinema SDR-to-HDR Mapping in a Controlled Mastering Workflow: A Pixel-wise Case Study on ASC StEM2
-
Channel importance boosts machine vision codec performance
CI-ICM: Channel Importance-driven Learned Image Coding for Machines
-
Mach hits 1.1 trillion points per second in ultrasound beamforming
mach: ultrafast ultrasound beamforming
-
Event overlay lifts robot pick success from 0% to 90% in dark
E-VLA: Event-Augmented Vision-Language-Action Model for Dark and Blurred Scenes
-
AI assistant in exams shows no effect on scores
An AI Teaching Assistant for Motion Picture Engineering
-
Bit partitioning lets one PE run FP8 or dual FP4 with 60% less area
DHFP-PE: Dual-Precision Hybrid Floating Point Processing Element for AI Acceleration