• Publications
  • Influence
A Survey of General-Purpose Computation on Graphics Hardware
The techniques used in mapping general-purpose computation to graphics hardware will be generally useful for researchers who plan to develop the next generation of GPGPU algorithms and techniques.
Real-time volume graphics
This course will learn techniques for harnessing the power of consumer graphics hardware and high-level shading languages for real-time rendering of volumetric data and effects, covering local and global illumination, scattering, pre-integration, implicit surfaces and non-polygonal isosurfaces, transfer function design, volume animation and deformation.
Interactive reconstruction of Monte Carlo image sequences using a recurrent denoising autoencoder
This work proposes a variant of deep convolutional networks better suited to the class of noise present in Monte Carlo rendering, which allows for much larger pixel neighborhoods to be taken into account, while also improving execution speed by an order of magnitude.
GPGPU: general-purpose computation on graphics hardware
The graphics processor (GPU) on today's commodity video cards has evolved into an extremely powerful and flexible processor. Modern graphics architectures provide tremendous memory bandwidth and
A Survey of General‐Purpose Computation on Graphics Hardware
This report describes, summarize, and analyzes the latest research in mapping general‐purpose computation to graphics hardware.
Towards foveated rendering for gaze-tracked virtual reality
A practical foveated rendering system that reduces number of shades by up to 70% and allows coarsened shading up to 30° closer to the fovea than Guenter et al.
GPGPU: general purpose computation on graphics hardware
This course provides a detailed introduction to general purpose computation on graphics hardware (GPGPU), emphasize core computational building blocks, ranging from linear algebra to database queries, and review the tools, perils, and tricks of the trade in GPU programming.
Spatiotemporal variance-guided filtering: real-time reconstruction for path-traced global illumination
A reconstruction algorithm is introduced that generates a temporally stable sequence of images from one path-per-pixel global illumination, using temporal accumulation to increase the effective sample count and spatiotemporal luminance variance estimates to drive a hierarchical, image-space wavelet filter.
Adaptive transparency
This work demonstrates that adaptive transparency is five to forty times faster than realtime A-buffer implementations, closely matches the image quality, and is both higher quality and faster than other approximate order-independent transparency techniques: stochastic transparency, uniform opacity shadow maps, and Fourier opacity mapping.
Particle‐Based Simulation of Fluids
A particle interaction method for simulating fluids using moving particles and their interactions that fits well into the current user interaction paradigm and allows easy user control over the desired fluid motion.