GPU-Based Inverse Rendering With Multi-Objective Particle Swarm Optimization
University of Southern California
SIGGRAPH Asia 2015 Visualization in High Performance Computing (SA ’15), 2015
@inproceedings{nagano2015gpu,
title={GPU-based inverse rendering with multi-objective particle swarm optimization},
author={Nagano, Koki and Collins, Thomas and Chen, Chi-An and Nakano, Aiichiro},
booktitle={SIGGRAPH Asia 2015 Visualization in High Performance Computing},
pages={8},
year={2015},
organization={ACM}
}
We present a novel, GPU-accelerated per-pixel inverse rendering (IR) optimization algorithm based on Particle Swarm Optimization (PSO), IRPSO. IRPSO estimates the per-pixel scene attributes including reflectance properties of a 3D model, and is fast enough to do in situ visualization of the optimization in real-time. We utilize the GPU framebuffer as a computational domain, where each pixel is treated as an independent computational "swarm". We propose a parallel framework that recovers the reflectance at each pixel location in a massively parallel fashion. The algorithm’s high parallel efficiency is demonstrated through our GPU/GLSL shader implementation of the method. IRPSO is validated experimentally on examples including simulated ground truth images.
November 20, 2015 by hgpu
