Intel

Courses

Attention-Aware Rendering, Mobile Graphics, and Games

Sunday, 10 August 2:00 PM - 5:15 PM | Vancouver Convention Centre, West Building, Rooms 211-214

Rendering and design efficiency become critical when deploying computer graphics to mobile devices and games. This course addresses novel approaches to applying visual-attention models, based on low- and high-level characteristics, to propel attention-aware rendering computation. The result: perceptually optimized scalable algorithms for mobile platforms and game design.

By incorporating visual-attention estimation, perceptually optimized renderers for mobile platforms can dynamically ignore perceptually non-important details. Modern games and interactive applications are simultaneously deployed for computers, consoles, and mobile devices of diverse computational power. Complex effects including, but not limited to complex refraction and subsurface scattering that are standard in desktop computers, could scale efficiently in portable devices if they are attention-aware. Many games rely on search or target detection to solve riddles or find game objects. Adjusting the difficulty of a level could be facilitated by relocating objects estimated to attract attention. The course showcases through interactive content how employing a visual-attention model leads to efficient game design and demonstrates examples such as integration of a high-level saliency model in an LOD manager, enabling complex effects in low-power devices by applying them in regions that users will attend to.

Level

Introductory

Prerequisites

None.

Intended Audience

Graphics enthusiasts, game developers, and developers of 3D apps on mobile platforms who are interested in applying attention maps to gain efficiencies in computation.

Instructor(s)

Ann McNamara
Texas A&M University

Katerina Mania
Technical University of Crete

Laurent Itti
University of Southern California

George Koulieris
Technical University of Crete

Reynold Bailey
Rochester Institute of Technology