Related papers: Disentangled Diffusion Autoencoder for Harmonizati…
Most visual generative models compress images into a latent space before applying diffusion or autoregressive modelling. Yet, existing approaches such as VAEs and foundation model aligned encoders implicitly constrain the latent space…
In this work, we focus on exploring explicit fine-grained control of generative facial image editing, all while generating faithful facial appearances and consistent semantic details, which however, is quite challenging and has not been…
Data augmentation (DA) can significantly strengthen the electroencephalogram (EEG)-based seizure prediction methods. However, existing DA approaches are just the linear transformations of original data and cannot explore the feature space…
Generating realistic 3D Human-Human Interaction (HHI) requires coherent modeling of the physical plausibility of the agents and their interaction semantics. Existing methods compress all motion information into a single latent…
Diffusion autoencoders (DAEs) are typically formulated as a noise prediction model and trained with a linear-$\beta$ noise schedule that spends much of its sampling steps at high noise levels. Because high noise levels are associated with…
Generative modeling frameworks have emerged as an effective approach to capture high-dimensional image distributions from large datasets without requiring domain-specific knowledge, a capability essential for longitudinal disease…
Unsupervised anomaly detection has gained significant attention in the field of medical imaging due to its capability of relieving the costly pixel-level annotation. To achieve this, modern approaches usually utilize generative models to…
The generative learning phase of Autoencoder (AE) and its successor Denosing Autoencoder (DAE) enhances the flexibility of data stream method in exploiting unlabelled samples. Nonetheless, the feasibility of DAE for data stream analytic…
Existing hyperspectral image (HSI) super-resolution (SR) methods struggle to effectively capture the complex spectral-spatial relationships and low-level details, while diffusion models represent a promising generative model known for their…
Recently most successful image synthesis models are multi stage process to combine the advantages of different methods, which always includes a VAE-like model for faithfully reconstructing embedding to image and a prior model to generate…
Diffusion Probabilistic Models (DPMs) have shown a powerful capacity of generating high-quality image samples. Recently, diffusion autoencoders (Diff-AE) have been proposed to explore DPMs for representation learning via autoencoding. Their…
Deep learning models for medical image classification usually achieve promising results but typically rely on large, annotated datasets or standard transfer learning from ImageNet. Self-Supervised Learning (SSL) has emerged as a powerful…
We present Deep Compression Autoencoder (DC-AE), a new family of autoencoder models for accelerating high-resolution diffusion models. Existing autoencoder models have demonstrated impressive results at a moderate spatial compression ratio…
We show that high quality, diverse and realistic-looking diffusion-weighted magnetic resonance images can be synthesized using deep generative models. Based on professional neuroradiologists' evaluations and diverse metrics with respect to…
Image denoising is a fundamental problem in computational photography, where achieving high perception with low distortion is highly demanding. Current methods either struggle with perceptual quality or suffer from significant distortion.…
Purpose: In the present work we describe the correction of diffusion-weighted MRI for site and scanner biases using a novel method based on invariant representation. Theory and Methods: Pooled imaging data from multiple sources are subject…
Variational autoencoder (VAE) is one of the most common techniques in the field of medical image generation, where this architecture has shown advanced researchers in recent years and has developed into various architectures. VAE has…
As the rapid growth of high-speed and deep-tissue imaging in biomedical research, it is urgent to find a robust and effective denoising method to retain morphological features for further texture analysis and segmentation. Conventional…
Latent diffusion models for medical image super-resolution universally inherit variational autoencoders designed for natural photographs. We show that this default choice, not the diffusion architecture, is the dominant constraint on…
Domain shift is a problem commonly encountered when developing automated histopathology pipelines. The performance of machine learning models such as convolutional neural networks within automated histopathology pipelines is often…