Search Results for author:
Found 170 papers, 66 papers with code
A Survey on Diffusion Models for Inverse Problems
Diffusion models have become increasingly popular for generative modeling due to their ability to generate high-quality samples.
Fundus image enhancement through direct diffusion bridges
We propose FD3, a fundus image enhancement method based on direct diffusion bridges, which can cope with a wide range of complex degradations, including haze, blur, noise, and shadow.
Solving Video Inverse Problems Using Image Diffusion Models
Specifically, by drawing inspiration from the success of the recent decomposed diffusion sampler (DDS), our method treats the time dimension of a video as the batch dimension of image diffusion models and solves spatio-temporal optimization problems within denoised spatio-temporal batches derived from each image diffusion model.
Amortized Posterior Sampling with Diffusion Prior Distillation
We propose a variational inference approach to sample from the posterior distribution for solving inverse problems.
Self-Guided Generation of Minority Samples Using Diffusion Models
Experiments on benchmark real datasets demonstrate that our approach can greatly improve the capability of creating realistic low-likelihood minority instances over the existing techniques without the reliance on costly additional elements.
(Deep) Generative Geodesics
In this work, we propose to study the global geometrical properties of generative models.
Deep Diffusion Image Prior for Efficient OOD Adaptation in 3D Inverse Problems
However, adaptation of the prior is necessary when there exists a discrepancy between the training and testing distributions.
CFG++: Manifold-constrained Classifier Free Guidance for Diffusion Models
More specifically, inspired by the recent advancements of diffusion model-based inverse problem solvers (DIS), we reformulate text-guidance as an inverse problem with a text-conditioned score matching loss and develop CFG++, a novel approach that tackles the off-manifold challenges inherent in traditional CFG.
LDMol: Text-to-Molecule Diffusion Model with Structurally Informative Latent Space
With the emergence of diffusion models as the frontline of generative models, many researchers have proposed molecule generation techniques with conditional diffusion models.
MindFormer: A Transformer Architecture for Multi-Subject Brain Decoding via fMRI
More specifically, MindFormer incorporates two key innovations: 1) a novel training strategy based on the IP-Adapter to extract semantically meaningful features from fMRI signals, and 2) a subject specific token and linear layer that effectively capture individual differences in fMRI signals while synergistically combines multi subject fMRI data for training.
Unified Editing of Panorama, 3D Scenes, and Videos Through Disentangled Self-Attention Injection
While text-to-image models have achieved impressive capabilities in image generation and editing, their application across various modalities often necessitates training separate models.
Concept Weaver: Enabling Multi-Concept Fusion in Text-to-Image Models
While there has been significant progress in customizing text-to-image generation models, generating images that combine multiple personalized concepts remains challenging.
Spectral Motion Alignment for Video Motion Transfer using Diffusion Models
The evolution of diffusion models has greatly impacted video generation and understanding.
OTSeg: Multi-prompt Sinkhorn Attention for Zero-Shot Semantic Segmentation
The recent success of CLIP has demonstrated promising results in zero-shot semantic segmentation by transferring muiltimodal knowledge to pixel-level classification.
Ranked #1 on
Zero-Shot Semantic Segmentation
on COCO-Stuff
Ground-A-Score: Scaling Up the Score Distillation for Multi-Attribute Editing
Despite recent advancements in text-to-image diffusion models facilitating various image editing techniques, complex text prompts often lead to an oversight of some requests due to a bottleneck in processing text information.
Generalized Consistency Trajectory Models for Image Manipulation
Diffusion-based generative models excel in unconditional generation, as well as on applied tasks such as image editing and restoration.
DreamSampler: Unifying Diffusion Sampling and Score Distillation for Image Manipulation
Reverse sampling and score-distillation have emerged as main workhorses in recent years for image manipulation using latent diffusion models (LDMs).
DreamMotion: Space-Time Self-Similar Score Distillation for Zero-Shot Video Editing
Text-driven diffusion-based video editing presents a unique challenge not encountered in image editing literature: establishing real-world motion.
UNICORN: Ultrasound Nakagami Imaging via Score Matching and Adaptation
Nakagami imaging holds promise for visualizing and quantifying tissue scattering in ultrasound waves, with potential applications in tumor diagnosis and fat fraction estimation which are challenging to discern by conventional ultrasound B-mode images.
Latent Inversion with Timestep-aware Sampling for Training-free Non-rigid Editing
In this work, we propose a training-free approach for non-rigid editing with Stable Diffusion, aimed at improving the identity preservation quality without compromising editability.
Defining Neural Network Architecture through Polytope Structures of Dataset
Current theoretical and empirical research in neural networks suggests that complex datasets require large network architectures for thorough classification, yet the precise nature of this relationship remains unclear.
Patch-wise Graph Contrastive Learning for Image Translation
Recently, patch-wise contrastive learning is drawing attention for the image translation by exploring the semantic correspondence between the input and output images.
Breast Ultrasound Report Generation using LangChain
Breast ultrasound (BUS) is a critical diagnostic tool in the field of breast imaging, aiding in the early detection and characterization of breast abnormalities.
VMC: Video Motion Customization using Temporal Attention Adaption for Text-to-Video Diffusion Models
Text-to-video diffusion models have advanced video generation significantly.
Contrastive Denoising Score for Text-guided Latent Diffusion Image Editing
A promising recent approach in this realm is Delta Denoising Score (DDS) - an image editing technique based on Score Distillation Sampling (SDS) framework that leverages the rich generative prior of text-to-image diffusion models.
End-to-End Breast Cancer Radiotherapy Planning via LMMs with Consistency Embedding
Inspired by this, here we present RO-LMM, a multi-purpose, comprehensive large multimodal model (LMM) tailored for the field of radiation oncology.
Regularization by Texts for Latent Diffusion Inverse Solvers
The recent advent of diffusion models has led to significant progress in solving inverse problems, leveraging these models as effective generative priors.
LLM-driven Multimodal Target Volume Contouring in Radiation Oncology
Target volume contouring for radiation therapy is considered significantly more challenging than the normal organ segmentation tasks as it necessitates the utilization of both image and text-based clinical information.
scHyena: Foundation Model for Full-Length Single-Cell RNA-Seq Analysis in Brain
Single-cell RNA sequencing (scRNA-seq) has made significant strides in unraveling the intricate cellular diversity within complex tissues.
ED-NeRF: Efficient Text-Guided Editing of 3D Scene with Latent Space NeRF
These advancements have been extended to 3D models, enabling the generation of novel 3D objects from textual descriptions.
Prompt-tuning latent diffusion models for inverse problems
We propose a new method for solving imaging inverse problems using text-to-image latent diffusion models as general priors.
Ground-A-Video: Zero-shot Grounded Video Editing using Text-to-image Diffusion Models
However, when confronted with the complexities of multi-attribute editing scenarios, they exhibit shortcomings such as omitting or overlooking intended attribute changes, modifying the wrong elements of the input video, and failing to preserve regions of the input video that should remain intact.
Steerable Conditional Diffusion for Out-of-Distribution Adaptation in Imaging Inverse Problems
Denoising diffusion models have emerged as the go-to framework for solving inverse problems in imaging.
C-DARL: Contrastive diffusion adversarial representation learning for label-free blood vessel segmentation
Blood vessel segmentation in medical imaging is one of the essential steps for vascular disease diagnosis and interventional planning in a broad spectrum of clinical scenarios in image-based medicine and interventional medicine.
Generative AI for Medical Imaging: extending the MONAI Framework
We have implemented these models in a generalisable fashion, illustrating that their results can be extended to 2D or 3D scenarios, including medical images with different modalities (like CT, MRI, and X-Ray data) and from different anatomical areas.
Energy-Based Cross Attention for Bayesian Context Update in Text-to-Image Diffusion Models
Despite the remarkable performance of text-to-image diffusion models in image generation tasks, recent studies have raised the issue that generated images sometimes cannot capture the intended semantic contents of the text prompts, which phenomenon is often called semantic misalignment.
Unpaired Deep Learning for Pharmacokinetic Parameter Estimation from Dynamic Contrast-Enhanced MRI
DCE-MRI provides information about vascular permeability and tissue perfusion through the acquisition of pharmacokinetic parameters.
Improving Diffusion-based Image Translation using Asymmetric Gradient Guidance
Diffusion models have shown significant progress in image translation tasks recently.
Direct Diffusion Bridge using Data Consistency for Inverse Problems
To address this problem, we propose a modified inference procedure that imposes data consistency without the need for fine-tuning.
Data Topology-Dependent Upper Bounds of Neural Network Widths
This is then extended to a simplicial complex, deriving width upper bounds based on its topological structure.
Score-based Diffusion Models for Bayesian Image Reconstruction
This paper explores the use of score-based diffusion models for Bayesian image reconstruction.
Unpaired Image-to-Image Translation via Neural Schrödinger Bridge
Diffusion models are a powerful class of generative models which simulate stochastic differential equations (SDEs) to generate data from noise.
LLM-CXR: Instruction-Finetuned LLM for CXR Image Understanding and Generation
Many recent works have focused on training adapter networks that serve as an information bridge between image processing networks and LLMs; but presumably, in order to achieve maximum reasoning potential of LLMs on visual information as well, visual and language features should be allowed to interact more freely.
Highly Personalized Text Embedding for Image Manipulation by Stable Diffusion
Diffusion models have shown superior performance in image generation and manipulation, but the inherent stochasticity presents challenges in preserving and manipulating image content and identity.
Improving 3D Imaging with Pre-Trained Perpendicular 2D Diffusion Models
Diffusion models have become a popular approach for image generation and reconstruction due to their numerous advantages.
Zero-Shot Contrastive Loss for Text-Guided Diffusion Image Style Transfer
Diffusion models have shown great promise in text-guided image style transfer, but there is a trade-off between style transformation and content preservation due to their stochastic nature.
Decomposed Diffusion Sampler for Accelerating Large-Scale Inverse Problems
In this study, we propose a novel and efficient diffusion sampling strategy that synergistically combines the diffusion sampling and Krylov subspace methods.
Improving Medical Speech-to-Text Accuracy with Vision-Language Pre-training Model
Automatic Speech Recognition (ASR) is a technology that converts spoken words into text, facilitating interaction between humans and machines.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Zero-shot Generation of Coherent Storybook from Plain Text Story using Diffusion Models
Recent advancements in large scale text-to-image models have opened new possibilities for guiding the creation of images through human-devised natural language.
Don't Play Favorites: Minority Guidance for Diffusion Models
However, the conventional generation process of the diffusion models mostly yields majority samples (that lie on high-density regions of the manifold) due to their high likelihoods, making themselves ineffective and time-consuming for the minority generating task.
ZegOT: Zero-shot Segmentation Through Optimal Transport of Text Prompts
In particular, we introduce a novel Multiple Prompt Optimal Transport Solver (MPOT), which is designed to learn an optimal mapping between multiple text prompts and visual feature maps of the frozen image encoder hidden layers.
Minimizing Trajectory Curvature of ODE-based Generative Models
Based on the relationship between the forward process and the curvature, here we present an efficient method of training the forward process to minimize the curvature of generative trajectories without any ODE/SDE simulation.
Annealed Score-Based Diffusion Model for MR Motion Artifact Reduction
Motion artifact reduction is one of the important research topics in MR imaging, as the motion artifact degrades image quality and makes diagnosis difficult.
Single-round Self-supervised Distributed Learning using Vision Transformer
Despite the recent success of deep learning in the field of medicine, the issue of data scarcity is exacerbated by concerns about privacy and data ownership.
Parallel Diffusion Models of Operator and Image for Blind Inverse Problems
We show the efficacy of our method on two representative tasks -- blind deblurring, and imaging through turbulence -- and show that our method yields state-of-the-art performance, while also being flexible to be applicable to general blind inverse problems when we know the functional forms.
Bidirectional Generation of Structure and Properties Through a Single Molecular Foundation Model
The recent success of large foundation models in artificial intelligence has prompted the emergence of chemical pre-trained models.
Ranked #1 on
Molecular Property Prediction
on Clearance
Solving 3D Inverse Problems using Pre-trained 2D Diffusion Models
Diffusion models have emerged as the new state-of-the-art generative model with high quality samples, with intriguing properties such as mode coverage and high flexibility.
Self-supervised debiasing using low rank regularization
Specifically, we first pretrain a biased encoder in a self-supervised manner with the rank regularization, serving as a semantic bottleneck to enforce the encoder to learn the spuriously correlated attributes.
Training Debiased Subnetworks with Contrastive Weight Pruning
Neural networks are often biased to spuriously correlated features that provide misleading statistical evidence that does not generalize.
Ranked #2 on
Facial Attribute Classification
on bFFHQ
Diffusion-based Image Translation using Disentangled Style and Content Representation
Diffusion-based image translation guided by semantic texts or a single target image has enabled flexible style transfer which is not limited to the specific domains.
Diffusion Posterior Sampling for General Noisy Inverse Problems
Diffusion models have been recently studied as powerful generative inverse problem solvers, owing to their high quality reconstructions and the ease of combining existing iterative solvers.
Denoising MCMC for Accelerating Diffusion-Based Generative Models
Diffusion models are powerful generative models that simulate the reverse of diffusion processes using score functions to synthesize data from noise.
Diffusion Adversarial Representation Learning for Self-supervised Vessel Segmentation
Also, by adversarial learning based on the proposed switchable spatially-adaptive denormalization, our model estimates synthetic fake vessel images as well as vessel segmentation masks, which further makes the model capture vessel-relevant semantic information.
Magnitude and Angle Dynamics in Training Single ReLU Neurons
To understand learning the dynamics of deep ReLU networks, we investigate the dynamic system of gradient flow $w(t)$ by decomposing it to magnitude $w(t)$ and angle $\phi(t):= \pi - \theta(t) $ components.
Self-supervised Multi-modal Training from Uncurated Image and Reports Enables Zero-shot Oversight Artificial Intelligence in Radiology
Recent advances in vision-language models sheds a light on the long-standing problems of the oversight AI by the understanding both visual and textual concepts and their semantic correspondences.
Pyramidal Denoising Diffusion Probabilistic Models
Recently, diffusion model have demonstrated impressive image generation performances, and have been extensively studied in various computer vision tasks.
Progressive Deblurring of Diffusion Models for Coarse-to-Fine Image Synthesis
We further propose a blur diffusion as a special case, where each frequency component of an image is diffused at different speeds.
Patch-wise Deep Metric Learning for Unsupervised Low-Dose CT Denoising
The acquisition conditions for low-dose and high-dose CT images are usually different, so that the shifts in the CT numbers often occur.
Diffusion Deformable Model for 4D Temporal Medical Image Generation
Our proposed DDM is composed of the diffusion and the deformation modules so that DDM can learn spatial deformation information between the source and target volumes and provide a latent code for generating intermediate frames along a geodesic path.
Improving Diffusion Models for Inverse Problems using Manifold Constraints
Recently, diffusion models have been used to solve various inverse problems in an unsupervised manner with appropriate modifications to the sampling process.
Mitigating Out-of-Distribution Data Density Overestimation in Energy-Based Models
Deep energy-based models (EBMs), which use deep neural networks (DNNs) as energy functions, are receiving increasing attention due to their ability to learn complex distributions.
Multi-Task Distributed Learning using Vision Transformer with Random Patch Permutation
The widespread application of artificial intelligence in health research is currently hampered by limitations in data availability.
MR Image Denoising and Super-Resolution Using Regularized Reverse Diffusion
Our network, trained only with coronal knee scans, excels even on out-of-distribution in vivo liver MRI data, contaminated with complex mixture of noise.
One-Shot Adaptation of GAN in Just One CLIP
Specifically, our model employs a two-step training strategy: reference image search in the source generator using a CLIP-guided latent optimization, followed by generator fine-tuning with a novel loss function that imposes CLIP space consistency between the source and adapted generators.
Exploring Patch-wise Semantic Relation for Contrastive Learning in Image-to-Image Translation Tasks
Recently, contrastive learning-based image translation methods have been proposed, which contrasts different spatial locations to enhance the spatial correspondence.
Multi-Scale Hybrid Vision Transformer for Learning Gastric Histology: AI-Based Decision Support System for Gastric Cancer Treatment
Our results demonstrate that AI-assisted gastric endoscopic screening has a great potential for providing presumptive pathologic opinion and appropriate cancer treatment of gastric cancer in practical clinical settings.
Phase Aberration Robust Beamformer for Planewave US Using Self-Supervised Learning
Ultrasound (US) is widely used for clinical imaging applications thanks to its real-time and non-invasive nature.
AI can evolve without labels: self-evolving vision transformer for chest X-ray diagnosis through knowledge distillation
Although deep learning-based computer-aided diagnosis systems have recently achieved expert-level performance, developing a robust deep learning model requires large, high-quality data with manual annotation, which is expensive to obtain.
Support Vectors and Gradient Dynamics of Single-Neuron ReLU Networks
Understanding implicit bias of gradient descent for generalization capability of ReLU networks has been an important research topic in machine learning research.
Energy-Based Contrastive Learning of Visual Representations
Contrastive learning is a method of learning visual representations by training Deep Neural Networks (DNNs) to increase the similarity between representations of positive pairs (transformations of the same image) and reduce the similarity between representations of negative pairs (transformations of different images).
Come-Closer-Diffuse-Faster: Accelerating Conditional Diffusion Models for Inverse Problems through Stochastic Contraction
In this work, we show that starting from Gaussian noise is unnecessary.
DiffuseMorph: Unsupervised Deformable Image Registration Using Diffusion Model
Specifically, the deformation fields are generated by the conditional score function of the deformation between the moving and fixed images, so that the registration can be performed from continuous deformation by simply scaling the latent feature of the score.
Tunable Image Quality Control of 3-D Ultrasound using Switchable CycleGAN
In contrast to 2-D ultrasound (US) for uniaxial plane imaging, a 3-D US imaging system can visualize a volume along three axial planes.
Noise Distribution Adaptive Self-Supervised Image Denoising using Tweedie Distribution and Score Matching
Through extensive experiments, we demonstrate that the proposed method can accurately estimate noise models and parameters, and provide the state-of-the-art self-supervised image denoising performance in the benchmark dataset and real-world dataset.
Federated Split Task-Agnostic Vision Transformer for COVID-19 CXR Diagnosis
For example, this enables neural network training for COVID-19 diagnosis on chest X-ray (CXR) images without collecting patient CXR data across multiple hospitals.
CLIPstyler: Image Style Transfer with a Single Text Condition
In order to deal with such applications, we propose a new framework that enables a style transfer `without' a style image, but only with a text description of the desired style.
Noise2Score: Tweedie’s Approach to Self-Supervised Image Denoising without Clean Images
Recently, there has been extensive research interest in training deep networks to denoise images without clean reference. However, the representative approaches such as Noise2Noise, Noise2Void, Stein's unbiased risk estimator (SURE), etc.
Federated Split Vision Transformer for COVID-19 CXR Diagnosis using Task-Agnostic Training
For example, this enables neural network training for COVID-19 diagnosis on chest X-ray (CXR) images without collecting patient CXR data across multiple hospitals.
Performance Analysis of Fractional Learning Algorithms
Fractional learning algorithms are trending in signal processing and adaptive filtering recently.
Score-based diffusion models for accelerated MRI
Leveraging the learned score function as a prior, here we introduce a way to sample data from a conditional distribution given the measurements, such that the model can be readily used for solving inverse problems in imaging, especially for accelerated MRI.
DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulation
To mitigate these problems and enable faithful manipulation of real images, we propose a novel method, dubbed DiffusionCLIP, that performs text-driven image manipulation using diffusion models.
Federated Contrastive Learning for Privacy-Preserving Unpaired Image-to-Image Translation
In addition, by combining it with the pre-trained VGG network, the learnable part of the discriminator can be further reduced without impairing the image quality, resulting in two order magnitude reduction in the communication cost.
Privacy-preserving Task-Agnostic Vision Transformer for Image Processing
Inspired by the recent success of Vision Transformer (ViT), here we present a new distributed learning framework for image processing applications, allowing clients to learn multiple tasks with their private data.
Deep Learning for Ultrasound Beamforming
Diagnostic imaging plays a critical role in healthcare, serving as a fundamental asset for timely diagnosis, disease staging and management as well as for treatment choice, planning, guidance, and follow-up.
Federated CycleGAN for Privacy-Preserving Image-to-Image Translation
Although the recent federated learning (FL) allows a neural network to be trained without data exchange, the basic assumption of the FL is that all clients have their own training data from a similar domain, which is different from our image-to-image translation scenario in which each client has images from its unique domain and the goal is to learn image translation between different domains without accessing the target domain data.
Noise2Score: Tweedie's Approach to Self-Supervised Image Denoising without Clean Images
Recently, there has been extensive research interest in training deep networks to denoise images without clean reference.
Learning Dynamic Graph Representation of Brain Connectome with Spatio-Temporal Attention
Here, we propose STAGIN, a method for learning dynamic graph representation of the brain connectome with spatio-temporal attention.
Federated Split Task-Agnostic Vision Transformer for COVID-19 CXR Diagnosis
For example, this enables neural network training for COVID-19 diagnosis on chest X-ray (CXR) images without collecting patient CXR data across multiple hospitals.
Unsupervised Deep Learning Methods for Biological Image Reconstruction and Enhancement
Recently, deep learning approaches have become the main research frontier for biological image reconstruction and enhancement problems thanks to their high performance, along with their ultra-fast inference times.
Feature Disentanglement in generating three-dimensional structure from two-dimensional slice with sliceGAN
Hence, we combine sliceGAN with AdaIN to endow the model with the ability to disentangle the features and control the synthesis.
Simultaneous super-resolution and motion artifact removal in diffusion-weighted MRI using unsupervised deep learning
To the best of our knowledge, the proposed method is the first to tackle super-resolution and motion artifact correction simultaneously in the context of MRI using unsupervised learning.
Deep learning enables reference-free isotropic super-resolution for volumetric fluorescence microscopy
Volumetric imaging by fluorescence microscopy is often limited by anisotropic spatial resolution from inferior axial resolution compared to the lateral resolution.
Cycle-free CycleGAN using Invertible Generator for Unsupervised Low-Dose CT Denoising
Recently, CycleGAN was shown to provide high-performance, ultra-fast denoising for low-dose X-ray computed tomography (CT) without the need for a paired training dataset.
Vision Transformer using Low-level Chest X-ray Feature Corpus for COVID-19 Diagnosis and Severity Quantification
This situation is ideally suited for the Vision Transformer (ViT) architecture, where a lot of unlabeled data can be used through structural modeling by the self-attention mechanism.
CXR Segmentation by AdaIN-based Domain Adaptation and Knowledge Distillation
As segmentation labels are scarce, extensive researches have been conducted to train segmentation networks with domain adaptation, semi-supervised or self-supervised learning techniques to utilize abundant unlabeled dataset.
PyNET-CA: Enhanced PyNET with Channel Attention for End-to-End Mobile Image Signal Processing
Reconstructing RGB image from RAW data obtained with a mobile device is related to a number of image signal processing (ISP) tasks, such as demosaicing, denoising, etc.
Diagonal Attention and Style-based GAN for Content-Style Disentanglement in Image Generation and Translation
One of the important research topics in image generative models is to disentangle the spatial contents and styles for their separate control.
Missing Cone Artifacts Removal in ODT using Unsupervised Deep Learning in Projection Domain
Optical diffraction tomography (ODT) produces three dimensional distribution of refractive index (RI) by measuring scattering fields at various angles.
Vision Transformer for COVID-19 CXR Diagnosis using Chest X-ray Feature Corpus
Under the global COVID-19 crisis, developing robust diagnosis algorithm for COVID-19 using CXR is hampered by the lack of the well-curated COVID-19 data set, although CXR data with other disease are abundant.
Severity Quantification and Lesion Localization of COVID-19 on CXR using Vision Transformer
Under the global pandemic of COVID-19, building an automated framework that quantifies the severity of COVID-19 and localizes the relevant lesion on chest X-ray images has become increasingly important.
CycleQSM: Unsupervised QSM Deep Learning using Physics-Informed CycleGAN
In contrast to the conventional cycleGAN, our novel cycleGAN has only one generator and one discriminator thanks to the known dipole kernel.
Continuous Conversion of CT Kernel using Switchable CycleGAN with AdaIN
We also show that the quality of generated images can be further improved if intermediate kernel domain images are available.
DeepPhaseCut: Deep Relaxation in Phase for Unsupervised Fourier Phase Retrieval
Unlike the existing deep learning approaches that use a neural network as a regularization term or an end-to-end blackbox model for supervised training, our algorithm is a feed-forward neural network implementation of PhaseCut algorithm in an unsupervised learning framework.
Unsupervised MR Motion Artifact Deep Learning using Outlier-Rejecting Bootstrap Aggregation
Recently, deep learning approaches for MR motion artifact correction have been extensively studied.
AIM 2020 Challenge on Learned Image Signal Processing Pipeline
This paper reviews the second AIM learned ISP challenge and provides the description of the proposed solutions and results.
Switchable Deep Beamformer
Recent proposals of deep beamformers using deep neural networks have attracted significant attention as computational efficient alternatives to adaptive and compressive beamformers.
Unpaired Deep Learning for Accelerated MRI using Optimal Transport Driven CycleGAN
Recently, deep learning approaches for accelerated MRI have been extensively studied thanks to their high performance reconstruction in spite of significantly reduced runtime complexity.
AdaIN-Switchable CycleGAN for Efficient Unsupervised Low-Dose CT Denoising
The secondary auxiliary generator is needed to enforce the cycle-consistency, but the additional memory requirement and increases of the learnable parameters are the main huddles for cycleGAN training.
CycleMorph: Cycle Consistent Unsupervised Deformable Image Registration
However, the existing deep learning methods still have limitation in the preservation of original topology during the deformation with registration vector fields.
Two-Stage Deep Learning for Accelerated 3D Time-of-Flight MRA without Matched Training Data
Time-of-flight magnetic resonance angiography (TOF-MRA) is one of the most widely used non-contrast MR imaging methods to visualize blood vessels, but due to the 3-D volume acquisition highly accelerated acquisition is necessary.
OT-driven Multi-Domain Unsupervised Ultrasound Image Artifact Removal using a Single CNN
Unfortunately, in the current deep learning approaches, a dedicated neural network should be trained with matched training data for each specific artifact type.
Unsupervised CT Metal Artifact Learning using Attention-guided beta-CycleGAN
Metal artifact reduction (MAR) is one of the most important research topics in computed tomography (CT).
Pushing the Limit of Unsupervised Learning for Ultrasound Image Artifact Removal
Experimental results for various tasks such as deconvolution, speckle removal, limited data artifact removal, etc.
NTIRE 2020 Challenge on Perceptual Extreme Super-Resolution: Methods and Results
This paper reviews the NTIRE 2020 challenge on perceptual extreme super-resolution with focus on proposed solutions and results.
Deep Learning COVID-19 Features on CXR using Limited Training Data Sets
Under the global pandemic of COVID-19, the use of artificial intelligence to analyze chest X-ray (CXR) image for COVID-19 diagnosis and patient triage is becoming important.
Unsupervised Deep Learning for MR Angiography with Flexible Temporal Resolution
This is because high spatio-temporal resolution ground-truth images are not available for tMRA.
Geometric Approaches to Increase the Expressivity of Deep Neural Networks for MR Reconstruction
Recently, it was shown that an encoder-decoder convolutional neural network (CNN) can be interpreted as a piecewise linear basis-like representation, whose specific representation is determined by the ReLU activation patterns for a given input image.
Unsupervised Denoising for Satellite Imagery using Wavelet Subband CycleGAN
Recently, deep learning approaches have been extensively explored for the removal of noises in satellite imagery.
Understanding Graph Isomorphism Network for rs-fMRI Functional Connectivity Analysis
This understanding enables us to exploit CNN-based saliency map techniques for the GNN, which we tailor to the proposed GIN with one-hot encoding, to visualize the important regions of the brain.
Structured Low-Rank Algorithms: Theory, MR Applications, and Links to Machine Learning
In this survey, we provide a detailed review of recent advances in the recovery of continuous domain multidimensional signals from their few non-uniform (multichannel) measurements using structured low-rank matrix completion formulation.
Optimal Transport driven CycleGAN for Unsupervised Learning in Inverse Problems
To improve the performance of classical generative adversarial network (GAN), Wasserstein generative adversarial networks (W-GAN) was developed as a Kantorovich dual formulation of the optimal transport (OT) problem using Wasserstein-1 distance.
BOOSTING ENCODER-DECODER CNN FOR INVERSE PROBLEMS
However, the computation of the divergence term in SURE is difficult to implement in a neural network framework, and the condition to avoid trivial identity mapping is not well defined.
CycleGAN with a Blur Kernel for Deconvolution Microscopy: Optimal Transport Geometry
Deconvolution microscopy has been extensively used to improve the resolution of the wide-field fluorescent microscopy, but the performance of classical approaches critically depends on the accuracy of a model and optimization algorithms.
Adaptive and Compressive Beamforming Using Deep Learning for Medical Ultrasound
In ultrasound (US) imaging, various types of adaptive beamforming techniques have been investigated to improve the resolution and contrast-to-noise ratio of the delay and sum (DAS) beamformers.
Unsupervised Deformable Image Registration Using Cycle-Consistent CNN
Medical image registration is one of the key processing steps for biomedical image analysis such as cancer diagnosis.
Boosting CNN beyond Label in Inverse Problems
In this paper, we show that the recent unsupervised learning methods such as Noise2Noise, Stein's unbiased risk estimator (SURE)-based denoiser, and Noise2Void are closely related to each other in their formulation of an unbiased estimator of the prediction error, but each of them are associated with its own limitations.
Differentiated Backprojection Domain Deep Learning for Conebeam Artifact Removal
Conebeam CT using a circular trajectory is quite often used for various applications due to its relative simple geometry.
Which Contrast Does Matter? Towards a Deep Understanding of MR Contrast using Collaborative GAN
Thanks to the recent success of generative adversarial network (GAN) for image synthesis, there are many exciting GAN approaches that successfully synthesize MR image contrast from other images with different contrasts.
Blind Deconvolution Microscopy Using Cycle Consistent CNN with Explicit PSF Layer
In contrast to the recent CNN approaches for similar problem, the explicit PSF modeling layers improve the robustness of the algorithm.
Deep Learning-based Universal Beamformer for Ultrasound Imaging
In ultrasound (US) imaging, individual channel RF measurements are back-propagated and accumulated to form an image after applying specific delays.
Mumford-Shah Loss Functional for Image Segmentation with Deep Learning
This loss function is based on the observation that the softmax layer of deep neural networks has striking similarity to the characteristic function in the Mumford-Shah functional.
Image Reconstruction: From Sparsity to Data-adaptive Methods and Machine Learning
This paper focuses on the two most recent trends in medical image reconstruction: methods based on sparsity or low-rank models, and data-driven methods based on machine learning techniques.
CollaGAN : Collaborative GAN for Missing Image Data Imputation
In many applications requiring multiple inputs to obtain a desired output, if any of the input data is missing, it often introduces large amounts of bias.
Understanding Geometry of Encoder-Decoder CNNs
Encoder-decoder networks using convolutional neural network (CNN) architecture have been extensively used in deep learning literatures thanks to its excellent performance for various inverse problems.
Universal Deep Beamformer for Variable Rate Ultrasound Imaging
In particular, we design an end-to-end deep learning framework that can directly process sub-sampled RF data acquired at different subsampling rate and detector configuration to generate high quality ultrasound images using a single beamformer.
One Network to Solve All ROIs: Deep Learning CT for Any ROI using Differentiated Backprojection
The first type learns ROI size-specific cupping artifacts from the analytic reconstruction images, whereas the second type network is to learn to invert the finite Hilbert transform from the truncated differentiated backprojection (DBP) data.
Cycle Consistent Adversarial Denoising Network for Multiphase Coronary CT Angiography
Although this reduces the total radiation dose, the image quality during the low-dose phases is significantly degraded.
k-Space Deep Learning for Parallel MRI: Application to Time-Resolved MR Angiography
Time-resolved angiography with interleaved stochastic trajectories (TWIST) has been widely used for dynamic contrast enhanced MRI (DCE-MRI).
k-Space Deep Learning for Reference-free EPI Ghost Correction
Reconstruction results using 3T and 7T in-vivo data showed that the proposed method outperformed the image quality compared to the existing methods, and the computing time is much faster. The proposed k-space deep learning for EPI ghost correction is highly robust and fast, and can be combined with acceleration, so that it can be used as a promising correction tool for high-field MRI without changing the current acquisition protocol.
k-Space Deep Learning for Accelerated MRI
The annihilating filter-based low-rank Hankel matrix approach (ALOHA) is one of the state-of-the-art compressed sensing approaches that directly interpolates the missing k-space data using low-rank Hankel matrix completion.
Ranked #6 on
Denoising
on Darmstadt Noise Dataset
Quantitative Susceptibility Map Reconstruction Using Annihilating Filter-based Low-Rank Hankel Matrix Approach
Quantitative susceptibility mapping (QSM) inevitably suffers from streaking artifacts caused by zeros on the conical surface of the dipole kernel in k-space.
Deep Residual Learning for Accelerated MRI using Magnitude and Phase Networks
The proposed deep residual learning networks are composed of magnitude and phase networks that are separately trained.
A Mathematical Framework for Deep Learning in Elastic Source Imaging
An inverse elastic source problem with sparse measurements is of concern.
Deep Learning Reconstruction for 9-View Dual Energy CT Baggage Scanner
For homeland and transportation security applications, 2D X-ray explosive detection system (EDS) have been widely used, but they have limitations in recognizing 3D shape of the hidden objects.
Deep Learning Interior Tomography for Region-of-Interest Reconstruction
Interior tomography for the region-of-interest (ROI) imaging has advantages of using a small detector and reducing X-ray radiation dose.
Efficient B-mode Ultrasound Image Reconstruction from Sub-sampled RF Data using Deep Learning
In portable, three dimensional, and ultra-fast ultrasound imaging systems, there is an increasing demand for the reconstruction of high quality images from a limited number of radio-frequency (RF) measurements due to receiver (Rx) or transmit (Xmit) event sub-sampling.
Deep Learning Diffuse Optical Tomography
Diffuse optical tomography (DOT) has been investigated as an alternative imaging modality for breast cancer detection thanks to its excellent contrast to hemoglobin oxidization level.
Deep Learning for Accelerated Ultrasound Imaging
In portable, 3-D, or ultra-fast ultrasound (US) imaging systems, there is an increasing demand to reconstruct high quality images from limited number of data.
Framing U-Net via Deep Convolutional Framelets: Application to Sparse-view CT
X-ray computed tomography (CT) using sparse projection views is a recent approach to reduce the radiation dose.
Deep Convolutional Framelet Denosing for Low-Dose CT via Wavelet Residual Network
To address this problem, we recently proposed a deep convolutional neural network (CNN) for low-dose X-ray CT and won the second place in 2016 AAPM Low-Dose CT Grand Challenge.
Deep Convolutional Framelets: A General Deep Learning Framework for Inverse Problems
Using numerical experiments with various inverse problems, we demonstrated that our deep convolution framelets network shows consistent improvement over existing deep architectures. This discovery suggests that the success of deep learning is not from a magical power of a black-box, but rather comes from the power of a novel signal representation using non-local basis combined with data-driven local basis, which is indeed a natural extension of classical signal processing theory.
Geometric GAN
Generative Adversarial Nets (GANs) represent an important milestone for effective generative models, which has inspired numerous variants seemingly different from each other.
Multi-Scale Wavelet Domain Residual Learning for Limited-Angle CT Reconstruction
Limited-angle computed tomography (CT) is often used in clinical applications such as C-arm CT for interventional imaging.
Wavelet Domain Residual Network (WavResNet) for Low-Dose X-ray CT Reconstruction
Model based iterative reconstruction (MBIR) algorithms for low-dose X-ray CT are computationally complex because of the repeated use of the forward and backward projection.
Deep Learning with Domain Adaptation for Accelerated Projection-Reconstruction MR
To address the situation given the limited available data, we propose a domain adaptation scheme that employs a pre-trained network using a large number of x-ray computed tomography (CT) or synthesized radial MR datasets, which is then fine-tuned with only a few radial MR datasets.
Deep artifact learning for compressed sensing and parallel MRI
Furthermore, the computational time is by order of magnitude faster.
Beyond Deep Residual Learning for Image Restoration: Persistent Homology-Guided Manifold Simplification
To address this issue, here we propose a novel feature space deep residual learning algorithm that outperforms the existing residual learning.
Ranked #6 on
Color Image Denoising
on CBSD68 sigma50
Deep Residual Learning for Compressed Sensing CT Reconstruction via Persistent Homology Analysis
Recently, compressed sensing (CS) computed tomography (CT) using sparse projection views has been extensively investigated to reduce the potential risk of radiation to patient.
A deep convolutional neural network using directional wavelets for low-dose X-ray CT reconstruction
To the best of our knowledge, this work is the first deep learning architecture for low-dose CT reconstruction that has been rigorously evaluated and proven for its efficacy.
Sparse + Low Rank Decomposition of Annihilating Filter-based Hankel Matrix for Impulse Noise Removal
The new approach, what we call the robust ALOHA, is motivated by the observation that an image corrupted with impulse noises has intact pixels; so the impulse noises can be modeled as sparse components, whereas the underlying image can be still modeled using a low-rank Hankel structured matrix.
