- No file added yet -
Transfer of albedo and local depth variation to photo-textures
conference contribution
posted on 2013-09-25, 14:14 authored by Francho Melendez, Mashhuda Glencross, Jon Starck, Gregory J. WardAcquisition of displacement and albedo maps for full building façades is a difficult problem and traditionally achieved through a labor intensive artistic process. In this paper, we present a material appearance transfer method, Transfer by Analogy, designed to infer surface detail and diffuse reflectance for textured surfaces like the present in building façades. We begin by acquiring small exemplars (displacement and albedo maps), in accessible areas, where capture conditions can be controlled. We then transfer these properties to a complete phototexture constructed from reference images and captured under diffuse daylight illumination. Our approach allows super-resolution inference of albedo and displacement from information in the photo-texture. When transferring appearance from multiple exemplars to façades containing multiple materials, our approach also sidesteps the need for segmentation. We show how we use these methods to create relightable models with a high degree of texture detail, reproducing the visually rich self-shadowing effects that would normally be difficult to capture using just simple consumer equipment. Copyright © 2012 by the Association for Computing Machinery, Inc.
History
School
- Science
Department
- Computer Science
Citation
MELENDEZ, F. ... et al., 2012. Transfer of albedo and local depth variation to photo-textures. IN: Proceedings of the 9th European Conference on Visual Media Production (CVMP'12), pp. 40 - 48Publisher
© ACMVersion
- AM (Accepted Manuscript)
Publication date
2012Notes
This is a conference paper. The published version is available at: http://dx.doi.org/10.1145/2414688.2414694ISBN
978-1-4503-1311-7Publisher version
Language
- en
Administrator link
Usage metrics
Licence
Exports
RefWorksRefWorks
BibTeXBibTeX
Ref. managerRef. manager
EndnoteEndnote
DataCiteDataCite
NLMNLM
DCDC