Related papers: FlowLensing: Simulating Gravitational Lensing with…
Modern applications of strong gravitational lensing require the ability to use precise and varied observational data to constrain complex lens models. I discuss two sets of computational methods for lensing calculations. The first is a new…
Using a layered representation for motion estimation has the advantage of being able to cope with discontinuities and occlusions. In this paper, we learn to estimate optical flow by combining a layered motion representation with deep…
We present the package Gravelamps which is designed to analyse lensed gravitational wave signals in order to constrain the mass density profile of the lensing object. Gravelamps does this via parameter estimation using the framework of…
Standard frame-based cameras that sample light intensity frames are heavily impacted by motion blur for high-speed motion and fail to perceive scene accurately when the dynamic range is high. Event-based cameras, on the other hand, overcome…
As the interferometers detecting gravitational waves are upgraded, improving their sensitivity, the probability of observing strong lensing increases. Once a detection is made, it will be critical to gain as much information as possible…
This work proposes an efficient method to enhance the quality of corrupted speech signals by leveraging both acoustic and visual cues. While existing diffusion-based approaches have demonstrated remarkable quality, their applicability is…
The reconstruction of unsteady flow fields from limited measurements is a challenging and crucial task for many engineering applications. Machine learning models are gaining popularity for solving this problem due to their ability to learn…
This paper investigates training better visual world models for robot manipulation, i.e., models that can predict future visual observations by conditioning on past frames and robot actions. Specifically, we consider world models that…
Next-generation galaxy surveys promise unprecedented precision in testing gravity at cosmological scales. However, realising this potential requires accurately modelling the non-linear cosmic web. We address this challenge by exploring…
Strong gravitational lensing offers a compelling test of the cold dark matter paradigm, as it allows for subhaloes with masses of $\sim10^{9}$ M$_\odot$ and below to be detected. We test commonly-used techniques for detecting subhaloes…
Diffusion models approximate the denoising distribution as a Gaussian and predict its mean, whereas flow matching models reparameterize the Gaussian mean as flow velocity. However, they underperform in few-step sampling due to…
We propose Functional Flow Matching (FFM), a function-space generative model that generalizes the recently-introduced Flow Matching model to operate in infinite-dimensional spaces. Our approach works by first defining a path of probability…
Gravitational Lensing is an efficient tool to probe: the mass distribution of collapsed systems: galaxies and clusters; high redshift objects thanks to the gravitational amplification; and the geometry of the Universe. I will review here…
Flow-matching generative models are increasingly used to simulate cell responses to biological perturbations. However, the design space for building such models is large and underexplored. We systematically analyse the design space of flow…
Self-supervised multi-frame methods have currently achieved promising results in depth estimation. However, these methods often suffer from mismatch problems due to the moving objects, which break the static assumption. Additionally,…
Deep learning-based generative models have emerged as powerful tools for modeling complex data distributions and generating high-fidelity samples, offering a transformative approach to efficiently explore the configuration space of…
Gravitational wave lensing, particularly microlensing by compact dark matter (DM), offers a unique avenue to probe the nature of dark matter. However, conventional detection methods are often computationally expensive, inefficient, and…
Optical flow estimation is a fundamental task in computer vision. Recent direct-regression methods using deep neural networks achieve remarkable performance improvement. However, they do not explicitly capture long-term motion…
Optical flow provides information on relative motion that is an important component in many computer vision pipelines. Neural networks provide high accuracy optical flow, yet their complexity is often prohibitive for application at the edge…
We introduce a new paradigm for generative modeling built on Continuous Normalizing Flows (CNFs), allowing us to train CNFs at unprecedented scale. Specifically, we present the notion of Flow Matching (FM), a simulation-free approach for…