Computer Scientist Rui Wang is fundamentally rethinking existing models and algorithms to develop innovations in the field of interactive visual computing.
Despite the tremendous progress in recent years, generating convincing imagery at interactive rates remains a major challenge in graphics - a challenge UMass Amherst computer scientist Rui Wang is meeting with his research aimed at enabling interactive visual computing exploiting modern graphics processors (GPUs).
In the physical world, trillions of photons can simultaneously interact with the scene, leading to an equilibrium state instantly; in the digital world, however, such complex interactions must be simulated with limited processing power. As a result, generating a photorealistic image often takes minutes to hours, limiting the user’s productivity.
Today’s GPUs have emerged as low-cost, massively parallel computation platforms with thousands of cores, high computation speed and memory bandwidth, often orders of magnitude higher than their CPU counterparts. Harnessing the GPU’s parallel processing capability can provide a cost effective solution to tackle computationally expensive tasks.
“Given these challenges, developing new algorithms to exploit the GPU is no longer a mere engineering practice, but requires fundamentally rethinking our existing models and algorithms,” notes Wang.
To this end, Wang’s research is focused on studying new mathematical models and efficient computational algorithms for visual computing, driven by the data-parallel architecture of GPUs. His research encompasses precomputed light transport, photorealistic rendering of dynamic scenes, and stochastic sampling.
Precomputed light transport (PLT) is a data-driven approach for interactive rendering with complex lighting. As the users can dynamically modify light sources on the fly, it is particularly useful for lighting design applications, and is increasingly being used in video games and commercial software. Wang has advanced the state-of-the-art by enabling dynamic material effects such as glossy surface reflections and translucency. This allows users to modify not only light sources, but also material properties interactively on the fly. He also has developed a GPU-based algorithm to speed up the process by adapting its underlying computations towards data-parallel and GPU-friendly models - a 10 to 50 times faster performance gain over an optimized CPU equivalent with the same rendering accuracy.
Together with collaborators at Zhejiang University in China, Wang also has developed the first GPU-based algorithm for fully dynamic scenes that integrates a wide range of lighting effects, including multi-bounce indirect lighting, glossy reflections, caustics, and arbitrary specular paths. The result is one to two orders of magnitude faster speed over traditional methods.
In digital image synthesis, stochastic sampling is a critical component and samples with good spectral distribution properties (such as blue noise) are essential for improving simulation speed, reducing aliasing artifacts, and for producing visually pleasing textures and patterns. Working with graduate student John Bowers, Wang has proposed the first GPU-based algorithm for computing blue noise samples on the surfaces of arbitrary 3D objects. Not only is their algorithm 10 times faster than the previous best-known algorithm, they have developed a new quantitative method to measure the spectral distribution quality of surface samples. Wang has also worked with graduate student Yahan Zhou to introduce the first algorithm that can generate samples with any user-specified distribution function. With an efficient GPU-based implementation, the user can interactively synthesize new samples that mimic the distribution property of any exemplar sample set.
Wang has worked extensively on using GPUs for more general-purpose computations as well, including, building efficient spatial data structures for high-dimensional datasets, creating geometric puzzles, and reconstructing 3D scenes.
“The rapid growth in GPU’s computation power will continue to expand the frontiers of visual computing in the future,” says Wang. “For sustained quality and speed improvements, it is essential to develop innovative algorithms and models that can adapt to the massively parallel architecture of the GPU. I hope to contribute new ideas and insights to help tackle some of the challenges in this direction.”
Abridged from the School of Computer Science "Significant Bits" Newsletter