Accurate 3D cardiac reconstruction from cine magnetic resonance imaging
...
DDIM inversion has revealed the remarkable potential of real image editi...
This paper shows that it is possible to learn models for monocular 3D
re...
Transformations based on domain expertise (expert transformations), such...
Diffusion models have achieved remarkable success in text-to-image
gener...
Human-AI complementarity is important when neither the algorithm nor the...
Recent works on diffusion models have demonstrated a strong capability f...
Can a text-to-image diffusion model be used as a training objective for
...
State-of-the-art (SOTA) semi-supervised learning (SSL) methods have been...
Despite the success of fully-supervised human skeleton sequence modeling...
Most methods for conditional video synthesis use a single modality as th...
Unlike traditional supervised learning, in many settings only partial
fe...
StyleGANs have shown impressive results on data generation and manipulat...
Conditional Generative Adversarial Networks (cGANs) extend the standard
...
Human-machine complementarity is important when neither the algorithm no...
Learning disentangled representations leads to interpretable models and
...
Auxiliary Classifier GANs (AC-GANs) are widely used conditional generati...
A key step in understanding the spatial organization of cells and tissue...
Conditional generative adversarial networks have shown exceptional gener...
Unsupervised domain adaptation (UDA) aims at inferring class labels for
...