Data-driven Color Manifolds
ACM Transaction on Graphics 2015

Data-driven Color Manifolds

Chuong H. Nguyen      Tobias Ritschel      Hans-Peter Seidel     

MPI Informatik      MMCI / Saarland University     

Our approach uses Internet image collections (1st col., only subset shown) to learn color manifolds. The 1D manifold for the class ``Banana'' with a single degree of freedom (2nd col., top) and as a patch for two degrees of freedom (2nd col., bottom). The same manifold shown as a 1D line (3rd col.) or a 2D patch (4th col.) in 3D color spaces. The same two colors are marked as squares in all visualizations. A key application is user interfaces where the manifold (here 1D) is used as a slider which show only the appropriate colors (6th col.) instead of all colors as in common color pickers (5th col.).

Abstract

Color selection is required in many computer graphics applications, but can be tedious, as 1D or 2D user interfaces are employed to navigate in a 3D color space. Until now the problem was considered a question of designing general color spaces with meaningful, e.g., perceptual, parameters. In this work, we show, how color selection usability improves by applying 1D or 2D color manifolds which predict the most likely change of color in a specific context. A typical use case is manipulating the color of a banana: instead of presenting a 2D+1D RGB, CIE Lab or HSV widget, our approach presents a simple 1D slider that captures the most likely change for this context. Technically, for each context we learn a lower-dimensional manifold with varying density from labeled Internet examples. We demonstrate the increase in task performance of color selection in a user study.

Materials

Related Publications

Guiding Image Manipulations using Shape-appearance Subspaces from Co-alignment of Image Collections Chuong H. Nguyen, Oliver Nalbach, Tobias Ritschel, Hans-Peter Seidel Computer Graphics Forum 34(2) (Proc. Eurographics, Zürich/Switzerland, 4th – 8th May 2015). Paper Video Project Page

Citation

Chuong H. Nguyen, Tobias Ritschel and Hans-Peter Seidel
Data-driven Color Manifolds
ACM Transactions on Graphics 34(2), 2015

@article{NguyenTOG2015,
  author = {Chuong H. Nguyen and Tobias Ritschel and Hans-Peter Seidel},
  title = {Data-driven Color Manifolds},  
  journal = {ACM Transactions On Graphics},
  volume = {34},
  number = {2},
  year = {2015}  
  }

ACM Transactions On Graphics © 2015. This is the author's version of the work. It is posted here by permission of ACM for your personal use, not for redistribution.