Photorealism of humans in computer animation

Computers

Photo-Realism of Humans in Computer Animation

A seamless incorporation between virtual objects and real environment in real time is one of the desired goals of computer animation. This goal is to have synthetic objects that are perfectly blended with real image background. The user perceives computer generated imagery that is indistinguishable from real ones as well as a part of surrounding real scenery. As well as matching geometric characteristics of virtual objects with real camera parameters, one important factor to achieve seamless blending is when virtual objects appear with a high level of photorealism as if they are formed by a mean of photography (Augusanto, 2004).

Having a common illumination for virtual objects and the real surrounding objects is the first necessary step if photorealistic quality is to be obtained. It gives a consistent look between synthetic and real surrounding objects and also visual subtleties such as inter-reflections and shadows. The illumination could be happening among virtual objects, or between virtual objects and real surrounding objects. The object is to create a sense of natural perception that can be developed from these visual cues, that would usually further lead to intuitive interaction towards virtual objects. The challenge to apply photorealistic rendering in augmented reality is difficult. This is because not only do the virtual objects have to look real but also visually consistent and coherent with respect to real environment, and yet, the rendering process must fit within real time requirement (Augusanto, 2004).

Computer animation can be found across a broad range of disciplines. The fast integration of computer animation technology into domestic, industrial, scientific and recreational spheres is evidence to both its versatility and disparity. An analysis of the filmic use of computer animation offers only a partial explanation of its development. "Computer animation is comprised of multiple histories across a variety of disciplines" (Surman, 2005).

The idea of cinematic realism has historically suggested the use of rational singular reality evoked by live action film photography. Since its beginning, animation has intrinsically and historically critiqued this singular hegemonic vision of reality. "In opposition to a singular reality, animation tends toward multiplicity in its critique of photographic naturalism" (Surman, 2005).

Recently there has been a breakthrough that is going to allow eextraordinarily lifelike characters are to begin appearing in films and computer games thanks to a new type of animation technology. This technology enables the minutest details of a facial expression to be captured and recreated. It is considered to be one of the first animations to have overleapt a long-standing barrier known as uncanny valley. This refers to the perception that animation looks less realistic as it approaches human likeness (Richards, 2008).

In producing this process researchers started with a video of an employee talking. Then they broke the facial movements down into dozens of smaller movements, each of which was given a control system. The aim was to overcome the traditional difficulties of animating a human face, for instance that the skin looks too shiny, or that the movements are too symmetrical (Richards, 2008).