Help Privacy Policy Disclaimer
  Advanced SearchBrowse





End-to-end Sampling Patterns


Leimkühler,  Thomas
Computer Graphics, MPI for Informatics, Max Planck Society;


Singh,  Gurprit
Computer Graphics, MPI for Informatics, Max Planck Society;


Myszkowski,  Karol       
Computer Graphics, MPI for Informatics, Max Planck Society;


Seidel,  Hans-Peter       
Computer Graphics, MPI for Informatics, Max Planck Society;

External Resource
No external resources are shared
Fulltext (restricted access)
There are currently no full texts shared for your IP range.
Fulltext (public)

(Preprint), 5MB

Supplementary Material (public)
There is no public supplementary material available

Leimkühler, T., Singh, G., Myszkowski, K., Seidel, H.-P., & Ritschel, T. (2018). End-to-end Sampling Patterns. Retrieved from http://arxiv.org/abs/1806.06710.

Cite as: https://hdl.handle.net/21.11116/0000-0002-1376-4
Sample patterns have many uses in Computer Graphics, ranging from procedural object placement over Monte Carlo image synthesis to non-photorealistic depiction. Their properties such as discrepancy, spectra, anisotropy, or progressiveness have been analyzed extensively. However, designing methods to produce sampling patterns with certain properties can require substantial hand-crafting effort, both in coding, mathematical derivation and compute time. In particular, there is no systematic way to derive the best sampling algorithm for a specific end-task. Tackling this issue, we suggest another level of abstraction: a toolkit to end-to-end optimize over all sampling methods to find the one producing user-prescribed properties such as discrepancy or a spectrum that best fit the end-task. A user simply implements the forward losses and the sampling method is found automatically -- without coding or mathematical derivation -- by making use of back-propagation abilities of modern deep learning frameworks. While this optimization takes long, at deployment time the sampling method is quick to execute as iterated unstructured non-linear filtering using radial basis functions (RBFs) to represent high-dimensional kernels. Several important previous methods are special cases of this approach, which we compare to previous work and demonstrate its usefulness in several typical Computer Graphics applications. Finally, we propose sampling patterns with properties not shown before, such as high-dimensional blue noise with projective properties.