Technical Report: Analyzing Visibility Configurations

Many algorithms, such as level of detail rendering and occlusion culling meth-ods, make decisions based on the degree of visibility of an object, but do not analyze the distribution or structure of the visible and occluded regions across surfaces. We present an efficient method to classify visibility configurations and show how this can be used to improve existing methods based on visibility de-termination. We adapt co-occurrence matrices for visibility analysis and employ machine learning techniques for a reliable classification. Our method enhances perceptually-motivated level of detail methods for interactive applications by detecting configurations with expected visual masking. We exemplify the versa-tility of our method with an analysis of area-light visibility configurations in ray tracing and an area-to-area visibility analysis suitable for hierarchical radiosity refinement. Our results demonstrate the robustness, simplicity and performance of our method in synthetic scenes as well as real applications