archive
Every paper Pith has read. Search by title, abstract, or pith.
837 papers in eess.IV · page 8
-
Radar model exits early on stabilized chirps to cut latency
RAVEN: Radar Adaptive Vision Encoders for Efficient Chirp-wise Object Detection and Segmentation
-
Triangular mask aligns blind spots with real camera noise
TM-BSN: Triangular-Masked Blind-Spot Network for Real-World Self-Supervised Image Denoising
-
Generative refinement segments microcalcifications without labels
MC-GenRef: Annotation-free mammography microcalcification segmentation with generative posterior refinement
-
Semantic priors from transformers reduce depth boundary artifacts
NAIMA: Semantics Aware RGB Guided Depth Super-Resolution
-
Cardiac MRI agent diagnoses seven diseases with 0.93 internal AUC
BAAI Cardiac Agent: An intelligent multimodal agent for automated reasoning and diagnosis of cardiovascular diseases from cardiac magnetic resonance imaging
-
Tree models beat deep learning for fruit ripeness using three wavelengths
Non-Destructive Prediction of Fruit Ripeness and Firmness Using Hyperspectral Imaging and Lightweight Machine Learning Models
-
Multi-scale fovea lowers costs in visual search attention
Cost-Efficient Multi-Scale Fovea for Semantic-Based Visual Search Attention
-
Noise injection turns diffusion denoisers into plug-and-play generative priors
Stochastic Generative Plug-and-Play Priors
-
AI pipeline turns raw phone photos into high-quality images
DRIFT: Deep Restoration, ISP Fusion, and Tone-mapping
-
Hypernetwork generates low-rank updates for unified chest CT model
HyperCT: Low-Rank Hypernet for Unified Chest CT Analysis
-
Neural diffusion codec beats H.264 lossless video
NeuralLVC: Neural Lossless Video Compression via Masked Diffusion with Temporal Conditioning
-
Self-consistent matching sharpens video at 2-4 steps
Salt: Self-Consistent Distribution Matching with Cache-Aware Training for Fast Video Generation
-
New dataset shows foreground degradations drive AR quality
ARIQA-3DS: A Stereoscopic Image Quality Assessment Dataset for Realistic Augmented Reality
-
Flow matching aligns images to lift medical segmentation by 4%
Few-Shot Distribution-Aligned Flow Matching for Data Synthesis in Medical Image Segmentation
-
Streaming 3D Gaussians improves viewpoint flexibility over video
Streaming Real-Time Rendered Scenes as 3D Gaussians
-
Adaptive frequency filter speeds neural signal fitting
Adaptive Local Frequency Filtering for Fourier-Encoded Implicit Neural Representations
-
One model restores remote sensing images from five degradations
Task-Guided Prompting for Unified Remote Sensing Image Restoration
-
MaskGen improves 3D biomedical segmentation across clinical shifts
Why Invariance is Not Enough for Biomedical Domain Generalization and How to Fix It
-
Diabetic retinopathy datasets limit reliable AI screening
Managing Diabetic Retinopathy with Deep Learning: A Data Centric Overview
-
Neural net recovers distance from stereo disparity gradients alone
QualiaNet: An Experience-Before-Inference Network
-
Hypergraph contrastive learning recovers 3D crowd meshes
Contrastive Multi-Modal Hypergraph Reasoning for 3D Crowd Mesh Recovery
-
Drifting models speed up high-quality MRI-to-CT synthesis
MRI-to-CT synthesis using drifting models
-
Efficiency turns video generators into world simulators
Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithms
-
Checksum vectors detect 97% of tape copies despite 75% data loss
Prints in the Magnetic Dust: Robust Similarity Search in Legacy Media Images Using Checksum Count Vectors
-
Satellite images predict full wireless channel responses
Deep Learning-Based Site-Specific Channel Modeling and Inference
-
Smartphone cameras match lab tools on sample concentrations
Quantitative measurements of biological/chemical concentrations using smartphone cameras
-
Semantic fields predict gaze in 360 video streams without training
Training-Free Adaptive 360-degree Video Streaming via Semantic Potential Fields
-
Unified training outperforms clinical groupings when ultrasound data is scarce
Understanding Task Aggregation for Generalizable Ultrasound Foundation Models
-
STAC cuts memory 10x for streaming 3D reconstruction
STAC: Plug-and-Play Spatio-Temporal Aware Cache Compression for Streaming 3D Reconstruction
-
Controller switches models to cut gesture energy 4x
Scale-Gest: Scalable Model-Space Synthesis and Runtime Selection for On-Device Gesture Detection
-
Tri-modal dataset and attentive model stage glaucoma
GLEAM: A Multimodal Imaging Dataset and HAMM for Glaucoma Classification
-
Union-find plus GRF yields exact clusters and analytical p-values
Hybrid eTFCE-GRF: Exact Cluster-Size Retrieval with Analytical p-Values for Voxel-Based Morphometry
-
Valid C2PA claim can assert human origin for AI-watermarked image
Authenticated Contradictions from Desynchronized Provenance and Watermarking
-
DICOM classifier uses cross-attention to handle missing metadata
Revisiting Integration of Image and Metadata for DICOM Series Classification: Cross-Attention and Dictionary Learning
-
Sparsity maps let MRI recon switch dictionaries and resist shifts
Learning spatially adaptive sparsity level maps for arbitrary convolutional dictionaries
-
Null-space graph smoothness lifts imaging PSNR by up to 4 dB
GSNR: Graph Smooth Null-Space Representation for Inverse Problems
-
Dropout training keeps glioblastoma segmentation accurate without FLAIR
Robust Glioblastoma Segmentation and Volumetry Without T2-FLAIR: External Validation of Targeted Dropout Training
-
Disentangling anatomy and style unifies 3D medical pretraining
MeDUET: Disentangled Unified Pretraining for 3D Medical Image Synthesis and Analysis
-
Gaussian surrogates match Poisson MAP error at low doses
Gaussian Surrogates for Poisson Imaging: Some Theoretical and Empirical Results
-
Recursive wavelets trim Gaussian counts in 3D splatting
Learnable Multi-level Discrete Wavelet Transforms for 3D Gaussian Splatting Frequency Modulation
-
Dynamic fMRI graphs align with frozen LLMs for autism diagnosis
NeuroMambaLLM: Dynamic Graph Learning of fMRI Functional Connectivity in Autistic Brains Using Mamba and Language Model Reasoning
-
Wavefield correlation lowers sound speed errors in ultrasound autofocusing
A Wavefield Correlation Approach to Improve Sound Speed Estimation in Ultrasound Autofocusing
-
MedXIAOHE beats closed medical AI on benchmarks via targeted training
MedXIAOHE: A Comprehensive Recipe for Building Medical MLLMs
-
Gradient maps detect CU steganography in HEVC videos
H.265/HEVC Video Steganalysis Based on CU Block Structure Gradients and IPM Mapping
-
Neural network leads in precision for sparse landmine detection
Benchmarking Deep Learning and Statistical Target Detection Methods for PFM-1 Landmine Detection in UAV Hyperspectral Imagery
-
Signal-space alignment stabilizes binary flow matching
Binary Flow Matching: Prediction-Loss Space Alignment for Robust Learning
-
U-net with distance loss yields consistent brain masks from MRI
Efficient Brain Extraction of MRI Scans with Mild to Moderate Neuropathology
-
RL router dynamically assigns medical cases to specialist AI agents
MedRoute: RL-Based Dynamic Specialist Routing in Multi-Agent Medical Diagnosis
-
AI orders MR-Linac prostate scans to detect daily changes
AI-Based Detection of Temporal Changes in MR-Linac Images Acquired During Routine Prostate Radiotherapy
-
Semantic retrieval lifts SAR target recognition accuracy
SAR-RAG: ATR Visual Question Answering by Semantic Search, Retrieval, and MLLM Generation