Elena Arabadzhiyska

Learn More
P Cs Rdiff Nw Ns Dfoc Rspec/gloss Figure 1: In a training phase (left), our approach learns a mapping from attributes in deferred shading buffers, e. g., positions, normals, reflectance, to RGB colors using a convolutional neural network (CNN). At runtime (right), the CNN is used to jointly shade with environment lighting and shadows as well as(More)
  • 1