Related papers: Diffusion Models for Probabilistic Deconvolution o…

We describe several projects addressing the growth of galaxies and massive black holes, for which adaptive optics is mandatory to reach high spatial resolution but is also a challenge due to the lack of guide stars and long integrations. In…

Diffusion models have emerged as powerful generative tools with applications in computer vision and scientific machine learning (SciML), where they have been used to solve large-scale probabilistic inverse problems. Traditionally, these…

Deep imaging of the diffuse light emitted by the stellar fine structures and outer halos around galaxies is now often used to probe their past mass assembly. Because the extended halos survive longer than the relatively fragile tidal…

Blending of galaxies has a major contribution in the systematic error budget of weak lensing studies, affecting photometric and shape measurements, particularly for ground-based, deep, photometric galaxy surveys, such as the Rubin…

We use the distribution of gravitationally-lensed image separations observed in the Cosmic Lens All-Sky Survey (CLASS) and the PMN-NVSS Extragalactic Lens Survey (PANELS), which are (nearly) complete for the image separation range $0''.3…

Classifier-free guidance (CFG) is a widely used technique for improving the perceptual quality of samples from conditional diffusion models. It operates by linearly combining conditional and unconditional score estimates using a guidance…

Diffusion probabilistic models (DPMs) have shown remarkable results on various image synthesis tasks such as text-to-image generation and image inpainting. However, compared to other generative methods like VAEs and GANs, DPMs lack a…

Generative models have attracted significant interest due to their ability to handle uncertainty by learning the inherent data distributions. However, two prominent generative models, namely Generative Adversarial Networks (GANs) and…

We introduce a novel method for weak-lensing measurements, which is based on a mathematically exact deconvolution of the moments of the apparent brightness distribution of galaxies from the telescope's PSF. No assumptions on the shape of…

Camera pose estimation is a long-standing computer vision problem that to date often relies on classical methods, such as handcrafted keypoint matching, RANSAC and bundle adjustment. In this paper, we propose to formulate the Structure from…

In the case of ground-based telescopes equipped with adaptive optics systems, the point spread function (PSF) is only poorly known or completely unknown. Moreover, an accurate modeling of the PSF is in general not available. Therefore in…

Lensless cameras replace bulky optics with thin modulation masks, enabling compact imaging systems. However, existing methods rely on an idealized model that assumes a globally shift-invariant point spread function (PSF) and sufficiently…

We present a masked-guided approach for a denoising diffusion probabilistic model (DDPM) trained to generate and inpaint realistic radio galaxy images. The inpainting capability is particularly relevant for reconstructing incomplete…

Score-based generative models (SGMs) have recently emerged as a promising class of generative models. However, a fundamental limitation is that their inference is very slow due to a need for many (e.g., 2000) iterations of sequential…

Diffusion models (DMs) have recently emerged as SoTA tools for generative modeling in various domains. Standard DMs can be viewed as an instantiation of hierarchical variational autoencoders (VAEs) where the latent variables are inferred…

Diffusion models offer stable training and state-of-the-art performance for deep generative modeling tasks. Here, we consider their use in the context of multivariate subsurface modeling and probabilistic inversion. We first demonstrate…

Galaxy image translation is an important application in galaxy physics and cosmology. With deep learning-based generative models, image translation has been performed for image generation, data quality enhancement, information extraction,…

Variational autoencoders (VAEs) are a popular class of deep generative models with many variants and a wide range of applications. Improvements upon the standard VAE mostly focus on the modelling of the posterior distribution over the…

Diffusion models are known for generating high-quality images, causing serious security concerns. To combat this, most efforts rely on deep neural networks (e.g., CNNs and Transformers), while largely overlooking the potential of…

We investigate the utility of meta-optical encoders for generalizable image compression by leveraging their intrinsic shift-invariant point spread functions (PSFs). Compared with purely digital approaches, such optical encoders offer…