UFig v1: The ultra-fast image generator
Silvan Fischbacher, Beatrice Moser, Tomasz Kacprzak, Luca Tortorelli, Joerg Herbel, Claudio Bruderer, Uwe Schmitt, Alexandre Refregier, Joel Berge, Lukas Gamper, Adam Amara

TL;DR
UFig v1 is a Python package that rapidly simulates realistic astronomical images, enabling efficient simulation-based inference by matching the speed of source extraction processes.
Contribution
It introduces a highly efficient, publicly available image generator for astronomy that integrates with existing analysis tools and supports emulators to accelerate simulations.
Findings
Simulation time matches source extraction time
Supports realistic galaxy and star sampling
Enables fast forward modeling in astronomy
Abstract
With the rise of simulation-based inference (SBI) methods, simulations need to be fast as well as realistic. is a public Python package that simulates astronomical images with exceptional speed, taking approximately the same time as source extraction. This makes it particularly well-suited for SBI methods where computational efficiency is crucial. To render an image, requires a galaxy catalog, and a description of the point spread function (PSF). It can also add background noise, sample stars using the Besan\c{c}on model of the Milky Way, and run to extract sources from the rendered image. The extracted sources can be matched to the intrinsic catalog, flagged based on output and survey masks, and emulators can be used to bypass the image simulation and extraction steps. A first version of was…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsImage Processing Techniques and Applications · Cell Image Analysis Techniques · Medical Image Segmentation Techniques
