Multi-Scale Terrain Texturing using Generative Adversarial Networks

Images

Bibtex

@INPROCEEDINGS{Klein-2010-TerrainSynthesis,
     author = {Klein, Jonathan and Hartmann, Stefan and Weinmann, Michael and Michels, Dominik L.},
      title = {Multi-Scale Terrain Texturing using Generative Adversarial Networks},
  booktitle = {Image and Vision Computing New Zealand},
       year = {2017},
  publisher = {IEEE},
   abstract = {We propose a novel, automatic generation process for detail maps that allows the reduction of tiling
               artifacts in real-time terrain rendering. This is achieved by training a generative adversarial
               network (GAN) with a single input texture and subsequently using it to synthesize a huge texture
               spanning the whole terrain. The low-frequency components of the GAN output are extracted,
               down-scaled and combined with the high-frequency components of the input texture during rendering.
               This results in a terrain texture that is both highly detailed and non-repetitive, which eliminates
               the tiling artifacts without decreasing overall image quality. The rendering is efficient regarding
               both memory consumption and computational costs. Furthermore, it is orthogonal to other techniques
               for terrain texture improvements such as texture splatting and can directly be combined with them.}
}