LGGRDec 17, 2017

Integral Equations and Machine Learning

arXiv:1712.06115v314 citations
Originality Synthesis-oriented
AI Analysis

This work addresses efficiency issues in light transport simulation for computer graphics, though it appears incremental as it applies known reinforcement learning methods to a specific domain.

The paper tackles the problem of improving efficiency in photorealistic image synthesis by using reinforcement learning techniques to guide light transport paths, based on the shared Fredholm integral equation with reinforcement learning, resulting in methods that train neural networks with standard information and generate arbitrary training samples.

As both light transport simulation and reinforcement learning are ruled by the same Fredholm integral equation of the second kind, reinforcement learning techniques may be used for photorealistic image synthesis: Efficiency may be dramatically improved by guiding light transport paths by an approximate solution of the integral equation that is learned during rendering. In the light of the recent advances in reinforcement learning for playing games, we investigate the representation of an approximate solution of an integral equation by artificial neural networks and derive a loss function for that purpose. The resulting Monte Carlo and quasi-Monte Carlo methods train neural networks with standard information instead of linear information and naturally are able to generate an arbitrary number of training samples. The methods are demonstrated for applications in light transport simulation.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes