Related papers: Improving style transfer in dynamic contrast enhan…
Latent diffusion models (LDMs) power state-of-the-art high-resolution generative image models. LDMs learn the data distribution in the latent space of an autoencoder (AE) and produce images by mapping the generated latents into RGB image…
Diffusion models have recently shown the ability to generate high-quality images. However, controlling its generation process still poses challenges. The image style transfer task is one of those challenges that transfers the visual…
Recent object detection models for infrared (IR) imagery are based upon deep neural networks (DNNs) and require large amounts of labeled training imagery. However, publicly available datasets that can be used for such training are limited…
Purpose: To apply tracer kinetic models as temporal constraints during reconstruction of under-sampled dynamic contrast enhanced (DCE) MRI. Methods: A library of concentration v.s time profiles is simulated for a range of physiological…
Computed tomography (CT) imaging could be very practical for diagnosing various diseases. However, the nature of the CT images is even more diverse since the resolution and number of the slices of a CT scan are determined by the machine and…
Analyzing temporal developments is crucial for the accurate prognosis of many medical conditions. Temporal changes that occur over short time scales are key to assessing the health of physiological functions, such as the cardiac cycle.…
Recent progress in contrastive learning has revolutionized unsupervised representation learning. Concretely, multiple views (augmentations) from the same image are encouraged to map to the similar embeddings, while views from different…
We propose a composable framework for latent space image augmentation that allows for easy combination of multiple augmentations. Image augmentation has been shown to be an effective technique for improving the performance of a wide variety…
Brain-computer interfaces (BCIs) harness electroencephalographic signals for direct neural control of devices, offering a significant benefit for individuals with motor impairments. Traditional machine learning methods for EEG-based motor…
In this work we address disentanglement of style and content in speech signals. We propose a fully convolutional variational autoencoder employing two encoders: a content encoder and a style encoder. To foster disentanglement, we propose…
Medical image segmentation is crucial for clinical diagnosis and treatment planning. Traditional methods typically produce a single segmentation mask, failing to capture inherent uncertainty. Recent generative models enable the creation of…
This paper presents a comprehensive study focused on disentangling hippocampal shape variations from diffusion tensor imaging (DTI) datasets within the context of neurological disorders. Leveraging a Mesh Variational Autoencoder (VAE)…
Generating realistic synthetic microscopy images is critical for training deep learning models in label-scarce environments, such as cell counting with many cells per image. However, traditional domain adaptation methods often struggle to…
We present Unified Contrastive Arbitrary Style Transfer (UCAST), a novel style representation learning and transfer framework, which can fit in most existing arbitrary image style transfer models, e.g., CNN-based, ViT-based, and flow-based…
Modelling multivariate spatio-temporal data with complex dependency structures is a challenging task but can be simplified by assuming that the original variables are generated from independent latent components. If these components are…
Large-scale text-to-image generative models have shown remarkable ability to synthesize diverse and high-quality images. However, it is still challenging to directly apply these models for editing real images for two reasons. First, it is…
Non-contrast CT (NCCT) imaging may reduce image contrast and anatomical visibility, potentially increasing diagnostic uncertainty. In contrast, contrast-enhanced CT (CECT) facilitates the observation of regions of interest (ROI). Leading…
A key requirement for the success of supervised deep learning is a large labeled dataset - a condition that is difficult to meet in medical image analysis. Self-supervised learning (SSL) can help in this regard by providing a strategy to…
Dark image enhancement aims at converting dark images to normal-light images. Existing dark image enhancement methods take uncompressed dark images as inputs and achieve great performance. However, in practice, dark images are often…
The deployment of autonomous agents in real-world scenarios is challenged by "unknown unknowns", i.e. novel unexpected environments not encountered during training, such as degraded signs. While existing research focuses on anomaly…