More talks in the program:
10:30 - 11:30
Deep learning holds a strong promise for computer graphics, from 3D rendering to content design generation or the creation of virtual worlds. Photo-realistic image rendering is the process that turns artificial models into larger than life images on the screen. Animators and game makers use costly rendering techniques called ray tracing to create high end images and videos. To fathom the high computational costs, consider that one frame of a Transformer character took an average of 250 hours and we need 30 frames for 1 second of an animated movie. In this session, I will go through some of the breakthrough work done to reduce the rendering time drastically, using deep learning with examples and codes. Moreover, we will explore with example codes and case studies the new frontiers of using advanced machine learning algorithms like Generative Modelling (GANs), reinforcement learning and neural style transfer for graphics-related tasks of image denoising, image impainting, and super resolution. The hacks to build real world AI-based graphics applications will also be covered.