Russell Croman Astrophotography  




Home | Free Trial | Purchase | Support

Hover over the photograph to see the original.

BlurXTerminator is an AI-based deconvolution tool designed specifically for astronomical images taken with equipment commonly used by amateur astrophotographers. It is available as a process module plug-in for PixInsight only.

Not all AI is created equal. AI-based sharpening tools for general photography exist but, when applied to astronomical images, they are prone to "inventing" detail that does not exist. They also don't usually handle stars very well. Their neural networks were not trained on astronomical images, so they often make bad "guesses" as to what the original, unblurred scene looks like.

The design intent of BlurXTerminator is to recover as much detail as possible based on low-contrast information actually present in an image, without fabricating detail that does not in fact exist just for the sake of an image that appears sharper. Great care has been taken in the architecture and training of the neural network to ensure that its output is as faithful as possible to reality if it is properly used.

All deconvolution, including the classical algorithms developed by Richardson, Lucy, van Cittert, and others, fundamentally involves guesswork. Mathematically, deconvolution is said to be an ill posed problem: for a given blurry input image, there are many possible sharper images that, if re-blurred, would result in the same input image. Which one is correct, or at least a better guess?

The classical algorithms use knowledge of an image's point spread function (PSF) to help guide deconvolution, which can be made to work as long as the PSF supplied to the algorithm is accurate. The application of neural networks to deconvolution brings an additional source of information to guide the process: knowledge of the structures and patterns typically present in real, high-resolution astronomical images. BlurXTerminator's neural network was trained using extremely high resolution images acquired by instruments such as the Hubble and James Webb space telescopes. It "understands" what astronomical structures actually look like at finer scales than can be resolved using amateur equipment.

The training methology additionally includes a deep understanding of the common point spread functions that astronomical images are subject to, including variations caused by atmospheric turbulence, optical scattering, acquisition issues such as guiding errors, and optical distortions such as coma and chromatic aberration. There is no need to extract the PSF ahead of time: BlurXTerminator uses the stars in an image as PSF references. It analyzes and processes an image in one step, with no iteration required in most cases.

BlurXTerminator can apply different amounts of deconvolution to the stellar and nonstellar features of an image. Trying to recover all of the detail available in nonstellar, extended objects using the classical algorithms usually results in dark halos (ringing) around stars. With BlurXTerminator, more sharpening can be applied to the nonstellar parts of an image, bringing out more detail without producing ringing artifacts in most cases.

BlurXTerminator can additionally correct for other aberrations present in an image in limited amounts. Among those currently comprehended for most instruments are:

  • Guiding errors
  • Astigmatism
  • Primary and secondary coma
  • Chromatic aberration (color fringing)
  • Varying star diameter (FWHM) and halos in each color channel

These aberrations are not assumed to be stationary: they can vary across the field of view. This is a major advantage over classical deconvolution algorithms that assume that the same PSF applies to the entire image. For example, stars with limited comatic profiles in the corners of an image will be made round and then sharpened, while stars in the center that are already round will simply be sharpened. This correction can be applied to the nonstellar features in an image, too. Correction can be done as a separate step, or in combination with sharpening.

Much more information about what BlurXTerminator does, how it does it, and how to use it can be found in the FAQ and in the documentation included in the download.

What about a Photoshop or Affinity Photo version of BlurXTerminator?

There are no plans to make a Photoshop or Affinity Photo plugin version of BlurXTerminator. Deconvolution is not just any sharpening algorithm: it has a precise mathematical definition. It requires linear image data with minimal processing for optimal results, or to even be called deconvolution. This is difficult to achieve using Photoshop and Affinity Photo: these tools are not inherently built to deal with linear astronomical images.

System Requirements

BlurXTerminator requires a computer with a modern CPU having instructions required to run neural networks. Older CPUs lacking FMA, AVX, and SSE instructions are not supported. Request a trial before purchasing to make sure it will work on your machine.

  • MacOS
    • Version 10.15 (Catalina) or later
    • PixInsight 1.8.8-9 or later
    • GPU/Neural Engine recommended for fast performance, but not required. Not all GPUs are supported.
    • Apple silicon neural engines (e.g., M1, M2) supported natively
  • Windows
    • Windows version 10 or later
    • Modern CPU capable of running neural networks (AVX, SSE instruction set extensions)
    • PixInsight 1.8.8-9 or later
  • Linux
    • Ubuntu 18.04 or later, or equivalent (glibc 2.27 or later required)
    • PixInsight 1.8.8-9 or later

PixInsight Module Version History

Version Date Comments
1.1.2 21 Jan 2023 MacOS only: corrected the selection of the appropriate AI file format (mlmodel vs. mlpackage) on certain MacOS 10.15 (Catalina) versions.
1.1.1 10 Jan 2023 Added luminance-only mode, improved consistency of aberration correction near the edges and corners of images, and enabled 32-bit floating point precision for MacOS 12 and later, improving accuracy and eliminating posterization in bright areas.
1.0.2 14 Dec 2022 Minor user interface refinement and documentation updates.
1.0.1 12 Dec 2022 Correctly finds the latest installed AI version by default.
1.0.0 8 Dec 2022 Initial release

AI Version History

Version Date Comments
2 10 Jan 2023 Improved preservation of star colors as well as general accuracy of deconvolution.
1 8 Dec 2022 Initial release