- Computer Graphics and Visualization Techniques
- Advanced Vision and Imaging
- 3D Shape Modeling and Analysis
- Parallel Computing and Optimization Techniques
- Data Visualization and Analytics
- Embedded Systems Design Techniques
- Distributed and Parallel Computing Systems
- Image Enhancement Techniques
- Advanced Image and Video Retrieval Techniques
- Interactive and Immersive Displays
- Computational Geometry and Mesh Generation
- 3D Surveying and Cultural Heritage
- Digital Image Processing Techniques
- Data Management and Algorithms
- Advanced Data Storage Technologies
- Advanced Database Systems and Queries
- Advanced Numerical Analysis Techniques
- Advanced Optical Imaging Technologies
- Interconnection Networks and Systems
- Formal Methods in Verification
- VLSI and Analog Circuit Testing
- Human Motion and Animation
- Design Education and Practice
- Augmented Reality Applications
- Logic, programming, and type systems
Stanford University
2015-2024
Princeton University
1990-2023
Stanford Medicine
2018
Palo Alto University
2013-2014
University of Limerick
2012
Laboratoire d'Informatique de Paris-Nord
1995-2010
Zero to Three
2008-2009
Penn Center for AIDS Research
2008-2009
Queues Enforth Development (United States)
2008-2009
University of Virginia
2008
Article Free Access Share on Light field rendering Authors: Marc Levoy Computer Science Department, Stanford University, Gates Building 3B, University Stanford, CA CAView Profile , Pat Hanrahan Authors Info & Claims SIGGRAPH '96: Proceedings of the 23rd annual conference graphics and interactive techniquesAugust 1996 Pages 31–42https://doi.org/10.1145/237170.237199Online:01 August 1996Publication History 2,352citation10,366DownloadsMetricsTotal Citations2,352Total Downloads10,366Last 12...
We present ShapeNet: a richly-annotated, large-scale repository of shapes represented by 3D CAD models objects. ShapeNet contains from multitude semantic categories and organizes them under the WordNet taxonomy. It is collection datasets providing many annotations for each model such as consistent rigid alignments, parts bilateral symmetry planes, physical sizes, keywords, well other planned annotations. Annotations are made available through public web-based interface to enable data...
A technique for rendering images of volumes containing mixtures materials is presented. The shading model allows both the interior a material and boundary between to be colored. Image projection performed by simulating absorption light along ray path eye. algorithms used are designed avoid artifacts caused aliasing quantization can efficiently implemented on an image computer. Images from variety applications shown.
In this paper, we present Brook for GPUs, a system general-purpose computation on programmable graphics hardware. extends C to include simple data-parallel constructs, enabling the use of GPU as streaming co-processor. We compiler and runtime that abstracts virtualizes many aspects addition, an analysis effectiveness compute engine compared CPU, determine when can outperform CPU particular algorithm. evaluate our with five applications, SAXPY SGEMV BLAS operators, image segmentation, FFT,...
This paper introduces a simple model for subsurface light transport in translucent materials. The enables efficient simulation of effects that BRDF models cannot capture, such as color bleeding within materials and diffusion across shadow boundaries. technique is even anisotropic, highly scattering media are expensive to simulate using existing methods. combines an exact solution single with dipole point source approximation multiple scattering. We also have designed new, rapid image-based...
This paper presents a many-core visual computing architecture code named Larrabee, new software rendering pipeline, manycore programming model, and performance analysis for several applications. Larrabee uses multiple in-order x86 CPU cores that are augmented by wide vector processor unit, as well some fixed function logic blocks. provides dramatically higher per watt unit of area than out-of-order CPUs on highly parallel workloads. It also greatly increases the flexibility programmability...
We consider the rendering of diffuse objects under distant illumination, as specified by an environment map. Using analytic expression for irradiance in terms spherical harmonic coefficients lighting, we show that one needs to compute and use only 9 coefficients, corresponding lowest-frequency modes order achieve average errors 1%. In other words, is insensitive high frequencies well approximated using parameters. fact, can be procedurally represented simply a quadratic polynomial cartesian...
In the last several years, large multidimensional databases have become common in a variety of applications, such as data warehousing and scientific computing. Analysis exploration tasks place significant demands on interfaces to these databases. Because size sets, dense graphical representations are more effective for than spreadsheets charts. Furthermore, because exploratory nature analysis, it must be possible analysts change visualizations rapidly they pursue cycle involving first...
Realism in computer-generated images requires accurate input models for lighting, textures and BRDFs. One of the best ways obtaining high-quality data is through measurements scene attributes from real photographs by inverse rendering. However, rendering methods have been largely limited to settings with highly controlled lighting. reasons this lack a coherent mathematical framework under general illumination conditions. Our main contribution introduction signal-processing which describes...
This paper presents a rapid hierarchical radiosity algorithm for illuminating scenes containing large polygonal patches. The constructs representation of the form factor matrix by adaptively subdividing patches into subpatches according to user-supplied error bound. guarantees that all factors are calculated same precision, removing many common image artifacts due inaccurate factors. More importantly, decomposes at most O(n) blocks (where n is number elements). Previous algorithms...
Recently a breakthrough has occurred in graphics hardware: fixed function pipelines have been replaced with programmable vertex and fragment processors. In the near future, pipeline is likely to evolve into general stream processor capable of more than simply feed-forward triangle rendering.In this paper, we evaluate these trends programmability explain how ray tracing can be mapped hardware. Using our simulator, analyze performance casting implementation on next generation addition, compare...
Article Free Access Share on Reflection from layered surfaces due to subsurface scattering Authors: Pat Hanrahan View Profile , Wolfgang Krueger Authors Info & Claims SIGGRAPH '93: Proceedings of the 20th annual conference Computer graphics and interactive techniquesSeptember 1993 Pages 165–174https://doi.org/10.1145/166117.166139Online:01 September 1993Publication History 298citation3,786DownloadsMetricsTotal Citations298Total Downloads3,786Last 12 Months136Last 6 weeks19 Get Citation...
This paper describes Show Me, an integrated set of user interface commands and defaults that incorporate automatic presentation into a commercial visual analysis system called Tableau. A key aspect Tableau is VizQL, language for specifying views, which used by Me to extend the generation tables views (commonly small multiple displays). research issue application experience, must support flow analysis. User experience has not been focus previous on presentation. The includes selection mark...
We present Sequoia, a programming language designed to facilitate the development of memory hierarchy aware parallel programs that remain portable across modern machines featuring different configurations. Sequoia abstractly exposes hierarchical in model and provides mechanisms describe communication vertically through machine localize computation particular locations within it. have implemented complete system, including compiler runtime systems for Cell processor-based blade distributed...
This paper presents a progressive refinement algorithm for volume rendering which uses pyramidal representation. Besides storing average values, the pyramid stores estimated error, so an octtree can be fit to given user-supplied precision. is then drawn using set of splats, or footprints, each scaled match size projection cell. The splats themselves are approximated with RGBA Gouraud-shaded polygons, that they efficiently on modern graphics workstations. result real-time suitable interactive...
We present a method for synthesizing 3D object arrangements from examples. Given few user-provided examples, our system can synthesize diverse set of plausible new scenes by learning larger scene database. rely on three novel contributions. First, we introduce probabilistic model based Bayesian networks and Gaussian mixtures that be trained small number input Second, develop clustering algorithm groups objects occurring in database according to their local neighborhoods. These contextual...
Ray tracing has produced some of the most realistic computer generated pictures to date. They contain surface texturing, local shading, shadows, reflections and refractions. The major disadvantage ray results from its point-sampling approach. Because calculation proceeds ab initio at each pixel it is very CPU intensive may noticeable aliasing artifacts. It difficult take advantage spatial coherence because shapes refractions curved surfaces are so complex.
Article Realistic modeling and rendering of plant ecosystems Share on Authors: Oliver Deussen Otto-von-Guericke Univ. Magdeburg MagdeburgView Profile , Pat Hanrahan Stanford Univ., Stanford, CA CAView Bernd Lintermann ZKM Center for Art Media Karlsruhe KarlsruheView Radomír Měch Calgary, Alta., Matt Pharr Przemyslaw Prusinkiewicz Authors Info & Claims SIGGRAPH '98: Proceedings the 25th annual conference Computer graphics interactive techniquesJuly 1998 Pages...
We present a theoretical analysis of the relationship between incoming radiance and irradiance. Specifically, we address question whether it is possible to compute incident from knowledge irradiance at all surface orientations. This fundamental in computer vision inverse radiative transfer. show that can be viewed as simple convolution illumination, i.e., clamped cosine transfer function. Estimating then seen deconvolution operation. derive closed-form formula for terms spherical harmonic...
We present a method, based on pre-computed light transport, for real-time rendering of objects under all-frequency, time-varying illumination represented as high-resolution environment map. Current techniques are limited to small area lights, with sharp shadows, or large low-frequency very soft shadows. Our main contribution is approximate the map in wavelet basis, keeping only largest terms (this known non-linear approximation). obtain further compression by encoding transport matrix...