Adaptive Rendering with Linear Predictions
Adaptive Rendering with Linear Predictions

Disney: Adaptive Rendering with Linear Predictions

Disney is proposing 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.

Adaptive Rendering with Linear Predictions
Adaptive Rendering with Linear Predictions

To achieve their goal, they 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. The 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.

Adaptive Rendering with Linear Predictions
Adaptive Rendering with Linear Predictions

Since each linear model predicts multiple pixels within its optimal prediction interval, Disney 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.

Adaptive Rendering with Linear Predictions
Adaptive Rendering with Linear Predictions

They 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. Disney have demonstrated that our method outperforms previous methods numerically and visually with high performance ray tracing kernels such as OptiX and Embree.

Adaptive Rendering with Linear Predictions
Adaptive Rendering with Linear Predictions
Spread the love