B
Brian Curless
Researcher at University of Washington
Publications - 130
Citations - 28232
Brian Curless is an academic researcher from University of Washington. The author has contributed to research in topics: Computer science & Rendering (computer graphics). The author has an hindex of 59, co-authored 122 publications receiving 25934 citations. Previous affiliations of Brian Curless include Stanford University.
Papers
More filters
Book ChapterDOI
Fourier Analysis of the 2D Screened Poisson Equation for Gradient Domain Problems
TL;DR: Analysis of the structure of the spatial filters that solve the 2D screened Poisson equation reveals gradient scaling to be a well-defined sharpen filter that generalizes Laplacian sharpening, which itself can be mapped to gradient domain filtering.
Journal ArticleDOI
Animating pictures with stochastic motion textures
TL;DR: A semi-automatic approach is used, in which a human user segments the scene into a series of layers to be individually animated, and a "stochastic motion texture" is automatically synthesized using a spectral method, i.e., the inverse Fourier transform of a filtered noise spectrum.
Proceedings ArticleDOI
Using photographs to enhance videos of a static scene
Pravin Bhat,C. Lawrence Zitnick,Noah Snavely,Aseem Agarwala,Maneesh Agrawala,Michael F. Cohen,Brian Curless,Sing Bing Kang +7 more
TL;DR: A framework for automatically enhancing videos of a static scene using a few photographs of the same scene and a novel image-based rendering algorithm that can re-render the input video using the appearance of the photographs while preserving certain temporal dynamics such as specularities and dynamic scene lighting.
Proceedings ArticleDOI
3D puppetry: a kinect-based interface for 3D animation
TL;DR: This work presents a system for producing 3D animations using physical objects (i.e., puppets) as input and provides 6D virtual camera \\rev{and lighting} controls, which the puppeteer can adjust before, during, or after a performance.
Journal ArticleDOI
From range scans to 3D models
TL;DR: A pipeline is step through that takes the range data into a single geometric model and will conclude with a discussion of the future of range scanning.