Neurally-Guided Procedural Models: Amortized Inference for Procedural Graphics Programs using Neural Networks

TL;DR

This paper introduces neurally-guided procedural models that incorporate neural networks to learn how to satisfy constraints, significantly improving the efficiency of probabilistic inference in procedural graphics by reducing the number of samples needed.

Contribution

The paper proposes a novel approach to augment procedural models with neural networks trained to guide sampling, enabling faster and more efficient constraint satisfaction in graphics.

Findings

Neurally-guided models generate high-quality results with fewer samples.

They achieve up to 10x speedup over unguided models.

The method is effective on image-based constraints for L-system-like models.

Abstract

Probabilistic inference algorithms such as Sequential Monte Carlo (SMC) provide powerful tools for constraining procedural models in computer graphics, but they require many samples to produce desirable results. In this paper, we show how to create procedural models which learn how to satisfy constraints. We augment procedural models with neural networks which control how the model makes random choices based on the output it has generated thus far. We call such models neurally-guided procedural models. As a pre-computation, we train these models to maximize the likelihood of example outputs generated via SMC. They are then used as efficient SMC importance samplers, generating high-quality results with very few samples. We evaluate our method on L-system-like models with image-based constraints. Given a desired quality threshold, neurally-guided models can generate satisfactory results up to 10x faster than unguided models.