Paper Info
Title
Creating Texture Exemplars from Unconstrained Images
Abstract
Texture is an essential feature in modeling the appearance of objects and is instrumental in making virtual objects appear interesting and/or realistic. Unfortunately, obtaining textures is a labor intensive task requiring parameter tuning for procedural methods or careful photography and post-processing for natural images. Many texture synthesis techniques have been developed to generate textures of arbitrary spatial extent, but these techniques require the user to first produce an exemplar consisting solely of the desired texture. We present a fast method using diffusion manifolds to locate textures in unconstrained photographs, and extract exemplar tiles. The method requires the user to only specify a single point within the image containing the desired texture and the scale of the desired texture. The user may tune the result using simple interactions. The method is non-local, in the sense that the desired texture does not have to appear in a single contiguous region in the source image. This document is a summary of our work and system. A full account is available online.
Year
DOI
Venue
2013
10.1109/CADGraphics.2013.65
CAD/Graphics
Keywords
Field
DocType
feature extraction,image texture,learning (artificial intelligence),contiguous region,diffusion manifolds,exemplar tiles extraction,object appearance,parameter tuning,texture exemplars,texture generation,texture synthesis techniques,unconstrained image,unconstrained photographs,Image Processing,Texture Extraction
Computer vision,Projective texture mapping,Texture compression,Image texture,Bidirectional texture function,Computer science,Texture memory,Artificial intelligence,Texture atlas,Texture synthesis,Texture filtering
Conference
Citations 
PageRank 
References 
3
0.39
3
Authors
4
Name
Order
Citations
PageRank
Yitzchak David Lockerman180.78
Su Xue2493.82
Julie Dorsey32535182.80
Holly Rushmeier42294334.25