Adaptive Rendering with Linear Predictions

Bochang Moon1, Jose A. Iglesias-Guitian1, Sung-Eui Yoon2, Kenny Mitchell1

Disney Research Zurich1, KAIST2

ACM Transactions on Graphics (Proc. of SIGGRAPH 2015)

ARLP1 ARLP2 ARLP3 ARLP4
(a) Ours, 15 spp (8.3 s)
rMSE 0.00199
(b) MC input, 16 spp
rMSE 0.68832
(c) Ours,15 spp (8.3 s)
rMSE 0.00199
(d) Reference,16384 spp
Our adaptive rendering result in the Courtyard scene. Our method with 15 samples per pixel (spp) produces a high-quality reconstruction result and drastically reduces a relative mean squared error (rMSE) compared to a straight-forward method utilizing low discrepancy (LD) sampling patterns uniformly.

Abstract

We propose a new adaptive rendering algorithm that enhances the performance of Monte Carlo ray tracing by reducing the noise, i.e., variance, while preserving a variety of high-frequency edges in rendered images through a novel prediction based reconstruction. To achieve our goal, we iteratively build multiple, but sparse linear models. Each linear model has its prediction window, where the linear model predicts the unknown ground truth image that can be generated with an infinite number of samples. Our method recursively estimates prediction errors introduced by linear predictions performed with different prediction windows, and selects an optimal prediction window minimizing the error for each linear model. Since each linear model predicts multiple pixels within its optimal prediction interval, we can construct our linear models only at a sparse set of pixels in the image screen. Predicting multiple pixels with a single linear model poses technical challenges, related to deriving error analysis for regions rather than pixels, and has not been addressed in the field. We address these technical challenges, and our method with robust error analysis leads to a drastically reduced reconstruction time even with higher rendering quality, compared to state-of-the-art adaptive methods. We have demonstrated that our method outperforms previous methods numerically and visually with high performance ray tracing kernels such as OptiX and Embree.

Video (available to download in the last section)

Contents