Symposium on Visualization in High Performance Computing

FCFull Conference Pass (FC - All Days)
FC1Full Conference Pass (FC - 1-Day Only)
BCBasic Conference Pass
ExExhibits Only
ETElectronic Theater Ticket
RTReception Ticket
GPU-Based Inverse Rendering With Multi-Objective Particle Swarm Optimization
Monday, 02 November
16:00 - 18:00
Kobe Int’l Conference Center, Room 502, Level 5

GPU-Based Inverse Rendering With Multi-Objective Particle Swarm Optimization

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.


Koki Nagano , USC Institute for Creative Technologies

Thomas Collins , University of Southern California

Chi-An Chen , University of Southern California

Aiichiro Nakano , University of Southern California

Go Back