Related papers: TopoCellGen: Generating Histopathology Cell Topolo…

We take up the challenge of designing realistic computational models of large interacting cell populations. The goal is essentially to bring Gillespie's celebrated stochastic methodology to the level of an interacting population of cells.…

Automated synthesis of histology images has several potential applications in computational pathology. However, no existing method can generate realistic tissue images with a bespoke cellular layout or user-defined histology parameters. In…

Protein structure prediction and folding are fundamental to understanding biology, with recent deep learning advances reshaping the field. Diffusion-based generative models have revolutionized protein design, enabling the creation of novel…

Diffusion models have become a new generative paradigm for text generation. Considering the discrete categorical nature of text, in this paper, we propose GlyphDiffusion, a novel diffusion approach for text generation via text-guided image…

Generative models, especially Diffusion Models, have demonstrated remarkable capability in generating high-quality synthetic data, including medical images. However, traditional class-conditioned generative models often struggle to generate…

Acquiring aligned visuo-tactile datasets is slow and costly, requiring specialised hardware and large-scale data collection. Synthetic generation is promising, but prior methods are typically single-modality, limiting cross-modal learning.…

In computational pathology, understanding and generation have evolved along disparate paths: advanced understanding models already exhibit diagnostic-level competence, whereas generative models largely simulate pixels. Progress remains…

We present Surf-D, a novel method for generating high-quality 3D shapes as Surfaces with arbitrary topologies using Diffusion models. Previous methods explored shape generation with different representations and they suffer from limited…

Diffusion-based voxel prior modelling is challenging for the reconstruction of large-scale 3D porous microstructures. Due to the demanding requirements for simultaneously modelling both the continuous pore morphology and the discrete…

This work introduces NetDiff, an expressive graph denoising diffusion probabilistic architecture that generates wireless ad hoc network link topologies. Such networks, with directional antennas, can achieve unmatched performance when the…

Deep generative models have significantly advanced medical imaging analysis by enhancing dataset size and quality. Beyond mere data augmentation, our research in this paper highlights an additional, significant capacity of deep generative…

Graph generative models are essential across diverse scientific domains by capturing complex distributions over relational data. Among them, graph diffusion models achieve superior performance but face inefficient sampling and limited…

Anatomical atlases are widely used for population studies and analysis. Conditional atlases target a specific sub-population defined via certain conditions, such as demographics or pathologies, and allow for the investigation of…

A long-standing challenge is designing multi-scale structures with good connectivity between cells while optimizing each cell to reach close to the theoretical performance limit. We propose a new method for direct multi-scale topology…

Recent advances in generative modeling, namely Diffusion models, have revolutionized generative modeling, enabling high-quality image generation tailored to user needs. This paper proposes a framework for the generative design of structural…

Generative models have advanced significantly in realistic image synthesis, with diffusion models excelling in quality and stability. Recent multi-view diffusion models improve 3D-aware street view generation, but they struggle to produce…

Large-scale generative models have demonstrated impressive capabilities in producing visually compelling images, with increasing applications in medical imaging. However, they continue to grapple with hallucination challenges and the…

Talking head generation is a significant research topic that still faces numerous challenges. Previous works often adopt generative adversarial networks or regression models, which are plagued by generation quality and average facial shape…

Deep learning models have emerged as a powerful tool for various medical applications. However, their success depends on large, high-quality datasets that are challenging to obtain due to privacy concerns and costly annotation. Generative…

Recent advances in synthetic imaging open up opportunities for obtaining additional data in the field of surgical imaging. This data can provide reliable supplements supporting surgical applications and decision-making through computer…