Learning from Shader Program Traces

TL;DR

This paper introduces a novel approach to learn from program traces of procedural shaders, enabling improved image synthesis and simulation tasks by leveraging intermediate execution data rather than traditional pixel-based inputs.

Contribution

It presents a new method for learning from shader program traces, outperforming traditional RGB-based models in image generation and simulation tasks.

Findings

Models learn from program traces outperform RGB-based models.

Effective in denoising shader outputs and approximating complex shaders.

Applicable to non-imagery simulations like flock behavior.

Abstract

Deep learning for image processing typically treats input imagery as pixels in some color space. This paper proposes instead to learn from program traces of procedural fragment shaders -- programs that generate images. At each pixel, we collect the intermediate values computed at program execution, and these data form the input to the learned model. We investigate this learning task for a variety of applications: our model can learn to predict a low-noise output image from shader programs that exhibit sampling noise; this model can also learn from a simplified shader program that approximates the reference solution with less computation, as well as learn the output of postprocessing filters like defocus blur and edge-aware sharpening. Finally we show that the idea of learning from program traces can even be applied to non-imagery simulations of flocks of boids. Our experiments on a variety of shaders show quantitatively and qualitatively that models learned from program traces outperform baseline models learned from RGB color augmented with hand-picked shader-specific features like normals, depth, and diffuse and specular color.