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)
In computer vision, convolutional neural networks (CNNs) achieve unprecedented performance for inverse problems where RGB pixel appearance is mapped to attributes such as positions, normals or reflectance. In computer graphics, screen space shading has boosted the quality of real-time rendering, converting the same kind of attributes of a virtual scene back(More)
Gaze-contingent rendering shows promise in improving perceived quality by providing a better match between image quality and the human visual system requirements. For example, information about fixation allows rendering quality to be reduced in peripheral vision, and the additional resources can be used to improve the quality in the foveal region.(More)
  • 1