https://github.com/crowsonkb/ucs

Implements the CAM02-UCS (Luo et al. (2006)) forward transform.
https://github.com/crowsonkb/ucs

color-science theano

Last synced: 6 months ago
JSON representation

Implements the CAM02-UCS (Luo et al. (2006)) forward transform.

• Host: GitHub
• URL: https://github.com/crowsonkb/ucs
• Owner: crowsonkb
• License: mit
• Created: 2017-03-22T23:13:28.000Z (over 8 years ago)
• Default Branch: master
• Last Pushed: 2017-05-16T07:48:53.000Z (over 8 years ago)
• Last Synced: 2025-04-12T22:44:22.139Z (6 months ago)
• Topics: color-science, theano
• Language: Python
• Homepage:
• Size: 27.3 KB
• Stars: 4
• Watchers: 3
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.rst
  • License: LICENSE

Awesome Lists containing this project

README

          
ucs

===

Implements the CAM02-UCS (Luo et al. (2006), "`Uniform Colour Spaces Based on CIECAM02 Colour Appearance Model `_") forward transform symbolically, using Theano.

See also: `CIECAM02 and Its Recent Developments `_.

The forward transform is symbolically differentiable in Theano and it may be approximately inverted, subject to gamut boundaries, by constrained function minimization (e.g. projected gradient descent or `L-BFGS-B `_).

Package contents

----------------

- ``constants.py`` contains constants needed by CAM02-UCS and others which are merely useful.

- ``functions.py`` contains compiled Theano functions, as well as NumPy equivalents of other symbolic functions. It also contains ``ucs_to_srgb()`` and ``ucs_to_srgb_b()``, which approximately invert the CAM02-UCS forward transform with L-BFGS-B.

- ``symbolic.py`` implements the forward transform symbolically in Theano. The functions therein can be used to construct custom auto-differentiable loss functions to be subject to optimization.