Semi-automatic control for data-driven computer graphics

Many computer graphics applications remain in the domain of the specialist. They are typically characterized by complex user-directed tasks, often requiring proficiency in design, colour spaces, computer interaction and file management. Furthermore, the demands of this skill set are often exacerbated by an equally complex collection of image or object manipulation commands embedded in a variety of interface components. The complexity of these graphics applications often requires that the user possess a correspondingly high level of expertise; the user is often required to be both a skilled artist as well as possessing considerable technical competence. The focus of this research is to further democratize computer graphics by reducing the complexity of graphics applications. This will be achieved through semi-automation and by incorporating aesthetic constraints into graphics applications thereby increasing accessibility to the average user. To achieve this, I aim to develop novel data-driven techniques applied to principal graphics problems. Unlike analytic methods, data-driven graphics generates new graphics elements (such as materials, geometry, or motion) from existing data extracted from the real world. The proposed research applies to many graphics applications including video production, architectural design and all forms of digital entertainment.