Computer Graphics Stack Exchange is a question and answer site for computer graphics researchers and programmers. It only takes a minute to sign up.
Sign up to join this community
I am reading a paper TileGAN: Synthesis of Large-Scale Non-Homogeneous Textures available here, and in the section entitled Selected Applications of GANS (i.e. applications of Generative Adversarial networks), they make claim that recent papers in computer grahics apply GANs to :
A quick google search of this term does not yield great results for a definition of this word. What does the term "volumetric modeling" mean?
Volumetric Modeling usually refers to using a regular 3D grid of voxels, analogous to 2D pixels, to define properties of an object at points or small regions of space.
While more complex data might be stored at each voxel, often each contains a simple vector of values which can be interpreted directly as density or material properties for analysis and rendering. There is a whole literature on such techniques (search for Volume Rendering), often in the context of medical imaging where e.g. MRI scanners produce such data directly.
It is natural to consider extending techniques for generating images composed of 2D pixels to 3D voxels and modeling solids.
