Siggraph 2013 - Learning Based Compression for Real-Time Rendering of Surface Light Fields

Learning Based Compression for Real-Time Rendering of Surface Light Fields
Siggraph 2013
Ehsan Miandji, Joel Kronander, Jonas Unger
Media and Information Technology, Linköping University, Sweden

Figure: A scene rendererd using our approach is shown in (left). Close ups of the translucent teapot rendered using CPCA and our method are shown in (middle) and (right), respectively. The scene was rendered at 52 fps using our method and 35 fps using CPCA.

Abstract:

Photo-realistic image synthesis in real-time is a key challenge in computer graphics. A number of techniques where the light transport in a scene is pre-computed, compressed and used for real-time image synthesis have been proposed. In this work, we extend this idea and present a technique where the radiance distribution in a scene, including arbitrarily complex materials and light sources, is pre-computed using photo-realistic rendering techniques and stored as surface light fields (SLF) at each surface. An SLF describes the full appearance of each surface in a scene as a 4D function over the spatial and angular domains. An SLF is a complex data set with a large memory footprint often in the order of several GB per object in the scene. The key contribution in this work is a novel approach for compression of surface light fields that enables real-time rendering of complex scenes. Our learning-based compression technique is based on exemplar orthogonal bases (EOB), and trains a compact dictionary of full-rank orthogonal basis pairs with sparse coefficients. Our results outperform the widely used CPCA method in terms of storage cost, visual quality and rendering speed. Compared to PRT techniques for real-time global illumination, our approach is limited to static scenes but can represent high frequency materials and any type of light source in a unified framework.

Documents:
Paper: Poster abstract (.pdf) (2.2MB)
Supplementary video: Real-time rendering examples (.mov) (28MB)

Acknowledgements:
This project was funded by the Swedish Foundation for Strategic Research (SSF) through grant IIS11-0081, and Linköping University Center for Industrial Information Technology (CENIIT).

Jonas Unger 2019