Adaptive precision in texture mapping

Abstract

We introduce an adaptive, iterative technique for obtaining texture samples of arbitrary precision when synthesizing a computer-generated image. The technique is an improvement on the sum table texturing method. To motivate the technique we analyze the error properties of the sum-table method. Based on that analysis we propose using a combination of tables independently or together to obtain a better estimate, and analyze the error properties of such methods. We then propose a new technique for obtaining texture samples whose accuracy is a function of the texture and the image. As part of this technique we propose the use of an auxiliary table which contains local estimates of the texture variance. We show how the iteration of a given sample may be controlled by values from this table. We then analyze the error in this method, and present images which demonstrate the improvement.