Work

Neural Importance Sampling of Many Lights

Year: 2025

Type: conference-paper

Abstract: We propose a neural approach for estimating spatially varying light selection distributions to improve importance sampling in Monte Carlo rendering, particularly for complex scenes with many light sources. Our method uses a neural network to predict the light selection distribution at each shading point based on local information, trained by minimizing the KL-divergence between the learned and target distributions in an online manner. To efficiently manage hundreds or thousands of lights, we integrate our neural approach with light hierarchy techniques, where the network predicts cluster-level distributions and existing methods sample lights within clusters. Additionally, we introduce a residual learning strategy that leverages initial distributions from existing techniques, accelerating convergence during training. Our method achieves superior performance across diverse and challenging scenes.

Source: ACM SIGGRAPH Conference Papers (SIGGRAPH)

DOI: 10.1145/3721238.3730754

Authors: Pedro Figueiredo, Qihao He, Steve Bako, Nima Khademi Kalantari

Institution: Texas A&M University

Language: English

Topic: Computer Graphics and Visualization Techniques

Subfield: Computer Graphics and Computer-Aided Design

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funder: National Science Foundation

Award: CAREER: Sparse Sampling and Reconstruction for Rendering Through Per-Scene Optimization