Improved sparse-view CT images with deep learning sinogram interpolation.
problem Sparse-view CT images quality improvement with limited projection data.
method Combination of U-Net and residual learning for sinogram interpolation.
result Significantly improved CT image quality (RMSE and SSIM metrics) over standard methods.
ChronoMID uses neural networks to classify bone disease in mice from micro-CT scans.
problem Classifying bone disease in mice from micro-CT scans.
method ChronoMID applies cross-modal convolutional neural networks to incorporate temporal information from timestamps and difference images.
result The top-performing model achieved 99.54% accuracy, significantly outperforming a baseline CNN.
Deep learning boosts micro-CT image resolution and texture recovery.
problem Compensating for image resolution trade-offs in micro-CT imaging.
method EDSRGAN trained on a diverse dataset of uCT images.
result EDSRGAN outperforms other methods in texture recovery and resolution.
Generative adversarial networks reconstruct oolitic limestone micro-structures.
problem Stochastic image reconstruction of oolitic limestone micro-structures.
method Generative adversarial neural networks (GANs) for unsupervised learning.
result GANs accurately reconstruct oolitic limestone micro-structures.
GANs improve 3D petrophysical model generation.
problem Generating accurate 3D petrophysical models for reservoir studies.
method Differentiable neural networks, content and perceptual losses.
result GANs effectively generate conditioned 3D pore and reservoir-scale models.
Six AI solutions accurately detect growth plate planes in mice bone scans.
problem Manual, time-consuming, and variable bone growth plate detection in micro-CT scans.
method Prepared and annotated a dataset of 3D μCT scans, organized a challenge, and developed six computer vision solutions.
result Achieved mean absolute error of 1.91±0.87 planes from ground truth.
CatSIM measures image similarity robustly to small changes.
problem Measuring similarity between images, especially with small perturbations.
method Uses structural similarity image quality paradigm, robust to small location changes.
result Structural similarity between images rated higher when not entirely overlapping.
Develops statistical guarantees for image-to-image regression models.
problem Current image-to-image regression models lack statistical guarantees for model mistakes and hallucinations.
method Uncertainty quantification techniques with rigorous statistical guarantees for image-to-image regression problems.
result Derives uncertainty intervals around each pixel with formal mathematical guarantees.
AugurOne trains single image generators without GANs using image warps.
problem Training end-to-end single image generators without GANs.
method Non-affine augmentations of single input images for training an upscaling neural network.
result End-to-end training yields state-of-the-art performance on conditional generation tasks.
Image visibility graphs map images into graphs for processing and classification.
problem Mapping image structures into graphs for processing and classification.
method Introduced image visibility graphs (IVGs) and explored their use in image processing and classification.
result IVGs encapsulate relevant image structure information and are computationally efficient.
Paper analyzes learning from ghost imaging without reconstruction bottleneck.
problem High-speed cell classification bottleneck in ghost cytometry.
method Theoretical analysis of learning from ghost imaging without reconstruction.
result Theoretical analysis supports learning from ghost imaging without reconstruction.
Total variation denoising improves image quality adaptively.
problem Improving image quality from noisy data.
method Total variation regularization for image denoising.
result Denoised images converge to true images at a parametric rate.
Improves text-to-image generation with bidirectional capabilities.
problem Generating realistic images from text descriptions.
method Integrates text and image modalities using MMVR architecture with n-gram cost function and multiple sentences.
result Significant improvement in image quality over existing methods (over 20%).
Transmission imaging, as an important imaging technique widely used in astronomy, medical diagnosis, and biology science, has been shown in [49] quite different from reflection imaging used in our everyday life. Understanding the structures of images (the prior information) is important for designing, testing, and choo…
This paper tackles generating manifold-valued images using WGAN.
problem Generating manifold-valued images over natural images.
method Formulated a theorem of optimal transport for Wasserstein distance on manifolds, introduced a new WGAN framework.
result Proposed model generates more plausible manifold-valued images than competitors.
A new metric FRD improves comparing medical images.
problem Comparing medical images for distribution or domain differences.
method Developed a new metric FRD using standardized radiomic features.
result FRD outperforms other metrics in various medical imaging applications.
This study investigates how much knowledge from natural images can be transferred to pathology images.
problem Quantifying how much knowledge from natural images can be transferred to pathology images.
method Proposes a framework to quantify knowledge gain by a particular layer, conducts empirical investigation in pathology image centered transfer learning.
result Early layers of deep models can transfer knowledge to pathology image classification tasks.
Generates high-resolution images from low-resolution inputs.
problem Generating realistic images from low-resolution inputs.
method Latent Adversarial Generator (LAG) using perceptual loss.
result Samples of high-resolution images from low-resolution inputs.
BCD-Net uses identical CNN structures for image recovery in undersampled imaging.
problem Challenges in obtaining accurate images from undersampled or noisy measurements.
method Incorporates image mapping CNN into BCD signal recovery method using alternating direction method of multipliers.
result Significantly more accurate image recovery compared to existing methods.
Few-shot unsupervised image-to-image translation model learns from a few examples.
problem Current unsupervised image-to-image translation methods require many images at training time.
method Coupling adversarial training with a novel network design for few-shot learning.
result Model achieves effective few-shot image-to-image translation.
Generates synthetic laparoscopic images for training deep neural networks.
problem Lack of large labeled data sets for laparoscopic image processing.
method Unpaired image-to-image translation to generate realistic synthetic images.
result Synthetic data set improves liver segmentation performance without manual labeling.
Paper proposes a CNN-LSTM model for image denoising and reconstruction.
problem Challenging task of image denoising and reconstruction in computer vision.
method Proposes an encoder-decoder model with direct attention, using CNN for encoding and LSTM for decoding.
result Model can reconstruct clean images from highly corrupted ones, even when human understanding is difficult.
Content based image retrieval, a technique which uses visual contents of image to search images from large scale image databases according to users' interests. This paper provides a comprehensive survey on recent technology used in the area of content based face image retrieval. Nowadays digital devices and photo shari…
Generative Adversarial Networks optimize model parameters for image matching.
problem Optimizing model parameters for accurate image matching.
method Model-Assisted Generative Adversarial Network (GAN) to produce fake images matching true images.
result Best match model parameter values can minimize bias in image recognition.
PG-IM uses neural-symbolic programs to manipulate images.
problem Creating holistic image representations and manipulations.
method PG-IM detects patterns, induces symbolic programs, and manipulates images using a neural network.
result PG-IM learns from a single image and achieves superior performance.
Paper introduces LLISE for image structure learning using SSIM.
problem Image quality assessment using MSE or ℓ2 norm is not promising. method Locally Linear Image Structural Embedding (LLISE) using SSIM.
result LLISE captures image structure features and discriminates distortions.
Paper proposes method to generate images from text using GANs trained on uncaptioned images.
problem Limited captioned image datasets for text-to-image synthesis.
method Conditional GANs trained on uncaptioned images with an Image Captioning Module.
result Promising preliminary results compared to unconditional GANs.
Latent feature models are attractive for image modeling, since images generally contain multiple objects. However, many latent feature models ignore that objects can appear at different locations or require pre-segmentation of images. While the transformed Indian buffet process (tIBP) provides a method for modeling tra…
The paper analyzes relationships between various image models for restoration.
problem Unclear relationships among popular image models for restoration.
method Theoretical analysis and experimental study of image models.
result Improved denoising performance by combining multiple image models.
Framework translates images between domains without supervision.
problem Challenges in unsupervised image-to-image translation, especially handling multimodality.
method Proposes a Multimodal Unsupervised Image-to-Image Translation (MUNIT) framework, decomposing images into content and style codes.
result Demonstrates improved generation of diverse outputs from a single source image.
Deep models generate images with missing high-frequency details.
problem Malicious use of realistic deep-generated images.
method Analysis of Fourier spectrum discrepancies between real and generated images.
result Detection method achieves up to 99.2% accuracy in classifying real and generated images.
StrokeCoder uses Transformers to generate images from single examples.
problem Creating diverse images from a single example.
method Transformer Neural Network learns from a single path-based example to generate a set of images.
result The model can generate a large set of deviated images that still represent the original image's style and concept.
Deep learning enhances optical microscopy and image reconstruction.
problem Improving image data transformations in optical microscopy.
method Application of deep learning methods on optical microscopy and image reconstruction.
result Deep learning enables new transformations among different modes and modalities of microscopic imaging.
New method reconstructs images from fMRI data using unlabeled data.
problem Challenges in acquiring labeled data for fMRI-to-image reconstruction.
method Self-supervised training with Encoder-Decoder and Decoder-Encoder networks.
result Reconstruction network adapts to new unlabeled test data.
Improved self-supervised learning for document images.
problem Performance of self-supervised pre-training on document images is poor.
method Proposed context-aware alternatives and a novel multi-modal method.
result Novel method outperforms other self-supervised methods on document image classification.
This paper proposes synthetic augmentation for nuclei image segmentation in medical pathology.
problem Rare and time-consuming labeling of tumor nuclei images for semantic segmentation.
method Label-to-image translation to generate synthetic images.
result Synthetic augmentation improves segmentation accuracy.
Style generators can invertibly generate images, useful for image enhancement and animation.
problem Generating all possible images and maintaining invertibility are challenging for GANs.
method Proposed style generators are invertible and can generate all possible images.
result Style generators outperform other GANs and Deep Image Prior as image priors.
Synthesizing images of the eye fundus is a challenging task that has been previously approached by formulating complex models of the anatomy of the eye. New images can then be generated by sampling a suitable parameter space. In this work, we propose a method that learns to synthesize eye fundus images directly from da…
Two-layer model sparsifies image residuals for CT image reconstruction.
problem Image reconstruction from limited and corrupted data.
method Pre-learning a two-layer sparsifying transform model with block coordinate descent optimization.
result Preliminary experiments show the two-layer model improves CT image reconstruction from low-dose measurements.
Survey of deep learning methods for image captioning.
problem Generating accurate and complex image descriptions.
method Comprehensive review of deep learning techniques for image captioning.
result Analysis of strengths, limitations, and popular datasets in deep learning image captioning.
CollaGAN uses GANs to impute missing image data.
problem Missing data bias in applications requiring multiple inputs.
method Collaborative Generative Adversarial Network (CollaGAN) for multi-domain image imputation.
result CollaGAN produces higher quality imputed images than existing methods.
Project analyzes images' impact on sentiment analysis.
problem Understanding how images contribute to sentiment classification.
method Compared models using only images, only text, or both.
result Combined models improved sentiment classification accuracy.
OTRE uses OT to improve retinal images, outperforming existing methods.
problem Improving quality of non-mydriatic retinal images for accurate diagnoses.
method OT theory for image-to-image translation, regularization by enhancing.
result OTRE outperforms state-of-the-art methods on various retinal image tasks.
Generates synthetic lung nodule images for training.
problem Lack of source image data for training machine learning models.
method Autoencoder techniques for 3D shape generation.
result Produces high-quality synthetic 3D images.
Method screens similar capsule endoscopic images, reducing doctor workload and improving accuracy.
problem Time-consuming and high error rate in manual inspection of large numbers of similar capsule endoscopic images.
method Structural similarity analysis of visually salient areas and hierarchical clustering.
result 76% reduction in similar images, 100% lesion recall, 18-minute average play time.
SeqAttnGAN generates interactive images based on multi-turn text descriptions.
problem Interactive image editing with multi-turn textual commands.
method SeqAttnGAN uses a neural state tracker and GAN framework for sequential image generation and refinement.
result SeqAttnGAN outperforms state-of-the-art models on interactive image editing tasks.
SR-NAM maps low-res images to multiple high-res images realistically.
problem Mapping low-resolution images to multiple high-resolution images realistically.
method SR-NAM using Non-Adversarial Mapping (NAM) technique and a degradation model.
result Realistic degradation and down-sampling of high-resolution images.
LcGAN generates synthetic CT images for hemorrhagic lesion segmentation.
problem Scarce training data for hemorrhagic lesion segmentation.
method Lesion conditional Generative Adversarial Network (LcGAN) for synthetic image generation.
result Segmentation improved by 12.8% with synthetic data augmentation.