Appearance Modeling with Data Coherency

One of the most prominent goals of computer graphics is to generate images that look as real as photographs. Realistic computer graphics imagery has however proven to be quite challenging to produce, since the appearance of materials arises from complicated physical processes that are difficult to analytically model and
simulate, and image-based modeling of real material samples is often impractical due to the high-dimensional space of appearance data that needs to be acquired.

This thesis presents a general framework based on the inherent coherency in the appearance data of materials to make image-based appearance modeling more tractable. We observe that this coherence manifests itself as low-dimensional structure in the appearance data, and by identifying this structure we can take advantage of it to simplify the major processes in the appearance modeling pipeline. This framework consists of two key components, namely the coherence structure and the accompanying reconstruction method to fully recover the low-dimensional appearance data from sparse measurements. Our investigation of appearance coherency
has led to three major forms of low-dimensional coherence structure and three types of coherency-based reconstruction upon which our framework is built.

This coherence-based approach can be comprehensively applied to all the major elements of image-based appearance modeling, from data acquisition of real material samples to user-assisted modeling from a photograph, from synthesis of volumes to editing of material properties, and from efficient rendering algorithms to physical fabrication of objects. In this thesis we present several techniques
built on this coherency framework to handle various appearance modeling tasks both for surface reflections and subsurface scattering, the two primary physical components that generate material appearance. We believe that coherency-based appearance modeling will make it easier and more feasible for practitioners to
bring computer graphics imagery to life.