Tone Mapping Techniques and Color Image Difference in Global Illumination

Tone mapping is the final step of every rendering process. Due to display devices’ nonlinearities, reduced color gamuts and moderate dynamic ranges it is necessary to apply some mapping technique on the computed radiances. We described mapping methods that are considered to be state of the art today, and some newly developed techniques. The main contributions of this thesis in tone mapping techniques are interactive calibration of contrast and aperture, minimum information loss methods and incident light metering. The interactive calibration technique makes it possible to display a desired scene lighting atmosphere if the radiance values are rendered in fictitious units. Minimum information loss techniques are based, in a way, on the photographers’ approach. The mapping function is applied only on a certain radiance interval, which is chosen automatically. The original contrast of all pixels inside the interval is preserved. Furthermore, the bounded error version of the minimum loss method is an extension of Schlick’s method. The incident light metering method was inspired by the photographers’ approach, too. This method makes it possible to reproduce original colors faithfully. Even if the average reflectance of a scene is very low, or very high, this method will reproduce original colors, which is not the case with other methods. The idea is to measure the incident light using diffusors in the scene, and then to compute a scale factor based on the incident light and apply this scale factor on the computed radiances. Beside these, other tone mapping techniques are described in this work. We described Tumblin and Rushmeier’s mapping, Ward’s contrast based scale factor, the widely used mean value mapping, an exponential mapping introduced by Ferschin et al., Schlick’s mapping, a visibility matching tone operator introduced by Larson et al., and a model of visual adaptation proposed by Ferwerda et al. Unfortunately there is no ultimative solution to the tone mapping problem. Every method has its strengths and weaknesses, and the user should choose a method according to his or her needs. Finally, this thesis ends with a color image difference algorithm. A good image metric is often needed in computer graphics. The method described here is a perception based metric that operates in the original image space (there is no need for Fourier or wavelet transform), what makes the whole method fast and intuitive. This is the only method that stresses distance dependency explicitly.