Reconstructing Monte Carlo Errors as a Blue-noise in Screen Space

Abstract

We present a novel method that reconstructs the Monte Carlo errors of renderings as a blue-noise in screen space. To this end, we conform the statistic result of per-pixel integration to a precomputed blue-noise mask. Thanks to the property of bluenoise, more visual fidelity is achieved through renderings after the reconstruction. The method has two key features. First, its realization is fast and straightforward. Second, it produces stable blue-noise-error renderings regardless of the correlation of the integrands. The preliminary results present robust blue-noise spectra with promising visual improvements in the renderings.