Related papers: Galactic Alchemy: Deep Learning Map-to-Map Transla…
Unsupervised image-to-image translation aims at learning a mapping between two visual domains. However, learning a translation across large geometry variations always ends up with failure. In this work, we present a novel…
Cosmological simulations are a powerful tool to advance our understanding of galaxy formation and many simulations model key properties of real galaxies. A question that naturally arises for such simulations in light of high-quality…
Upcoming cosmological weak lensing surveys are expected to constrain cosmological parameters with unprecedented precision. In preparation for these surveys, large simulations with realistic galaxy populations are required to test and…
In recent years, deep learning models have been successfully employed for augmenting low-resolution cosmological simulations with small-scale information, a task known as "super-resolution". So far, these cosmological super-resolution…
The chemistry of an astrophysical environment is closely coupled to its dynamics, the latter often found to be complex. Hence, to properly model these environments a 3D context is necessary. However, solving chemical kinetics within a 3D…
Unsupervised domain mapping has attracted substantial attention in recent years due to the success of models based on the cycle-consistency assumption. These models map between two domains by fooling a probabilistic discriminator, thereby…
Understanding the impact of neutrino masses on the evolution of Universe is a crucial aspect of modern cosmology. Due to their large free streaming lengths, neutrinos significantly influence the formation of cosmic structures at non-linear…
A comprehensive understanding of vision and language and their interrelation are crucial to realize the underlying similarities and differences between these modalities and to learn more generalized, meaningful representations. In recent…
We train graph neural networks to perform field-level likelihood-free inference using galaxy catalogs from state-of-the-art hydrodynamic simulations of the CAMELS project. Our models are rotational, translational, and permutation invariant…
Supervised depth estimation has achieved high accuracy due to the advanced deep network architectures. Since the groundtruth depth labels are hard to obtain, recent methods try to learn depth estimation networks in an unsupervised way by…
Image-to-image translation plays a vital role in tackling various medical imaging tasks such as attenuation correction, motion correction, undersampled reconstruction, and denoising. Generative adversarial networks have been shown to…
In order to prepare for the upcoming wide-field cosmological surveys, large simulations of the Universe with realistic galaxy populations are required. In particular, the tendency of galaxies to naturally align towards overdensities, an…
Depth perception is a key component for autonomous systems that interact in the real world, such as delivery robots, warehouse robots, and self-driving cars. Tasks in autonomous robotics such as 3D object recognition, simultaneous…
State-of-the-art methods for image-to-image translation with Generative Adversarial Networks (GANs) can learn a mapping from one domain to another domain using unpaired image data. However, these methods require the training of one specific…
Cellular force transmission across a hierarchy of molecular switchers is central to mechanobiological responses. However, current cellular force microscopies suffer from low throughput and resolution. Here we introduce and train a…
High-resolution mapping of cosmic mass distribution is essential for a variety of astrophysical applications including understanding cosmic structure formation, and galaxy formation and evolution. However dark matter is not directly…
One highly promising direction for enabling flexible real-time on-device image editing is utilizing data distillation by leveraging large-scale text-to-image diffusion models to generate paired datasets used for training generative…
While cosmological dark matter-only simulations relying solely on gravitational effects are comparably fast to compute, baryonic properties in simulated galaxies require complex hydrodynamic simulations that are computationally costly to…
Generative adversarial networks (GANs) provide an algorithmic framework for constructing generative models with several appealing properties: they do not require a likelihood function to be specified, only a generating procedure; they…
The latest observations of molecular gas and the atomic hydrogen content of local and high-redshift galaxies, coupled with how these correlate with star formation activity, have revolutionized our ideas about how to model star formation in…