File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Inverse texture synthesis

TitleInverse texture synthesis
Authors
KeywordsGPU techniques
Texture mapping
Texture synthesis
Issue Date2008
PublisherAssociation for Computing Machinery, Inc
Citation
Acm Transactions On Graphics, 2008, v. 27 n. 3 How to Cite?
AbstractThe quality and speed of most texture synthesis algorithms depend on a 2D input sample that is small and contains enough texture variations. However, little research exists on how to acquire such sample. For homogeneous patterns this can be achieved via manual cropping, but no adequate solution exists for inhomogeneous or globally varying textures, i.e. patterns that are local but not stationary, such as rusting over an iron statue with appearance conditioned on varying moisture levels. We present inverse texture synthesis to address this issue. Our inverse synthesis runs in the opposite direction with respect to traditional forward synthesis: given a large globally varying texture, our algorithm automatically produces a small texture compaction that best summarizes the original. This small compaction can be used to reconstruct the original texture or to re-synthesize new textures under user-supplied controls. More important, our technique allows real-time synthesis of globally varying textures on a GPU, where the texture memory is usually too small for large textures. We propose an optimization framework for inverse texture synthesis, ensuring that each input region is properly encoded in the output compaction. Our optimization process also automatically computes orientation fields for anisotropic textures containing both low- and high-frequency regions, a situation difficult to handle via existing techniques. © 2008 ACM.
Persistent Identifierhttp://hdl.handle.net/10722/141794
ISSN
2015 Impact Factor: 4.218
2015 SCImago Journal Rankings: 2.552
ISI Accession Number ID
References

 

DC FieldValueLanguage
dc.contributor.authorWei, LYen_HK
dc.contributor.authorHan, Jen_HK
dc.contributor.authorZhou, Ken_HK
dc.contributor.authorBao, Hen_HK
dc.contributor.authorGuo, Ben_HK
dc.contributor.authorShum, HYen_HK
dc.date.accessioned2011-09-27T03:02:02Z-
dc.date.available2011-09-27T03:02:02Z-
dc.date.issued2008en_HK
dc.identifier.citationAcm Transactions On Graphics, 2008, v. 27 n. 3en_HK
dc.identifier.issn0730-0301en_HK
dc.identifier.urihttp://hdl.handle.net/10722/141794-
dc.description.abstractThe quality and speed of most texture synthesis algorithms depend on a 2D input sample that is small and contains enough texture variations. However, little research exists on how to acquire such sample. For homogeneous patterns this can be achieved via manual cropping, but no adequate solution exists for inhomogeneous or globally varying textures, i.e. patterns that are local but not stationary, such as rusting over an iron statue with appearance conditioned on varying moisture levels. We present inverse texture synthesis to address this issue. Our inverse synthesis runs in the opposite direction with respect to traditional forward synthesis: given a large globally varying texture, our algorithm automatically produces a small texture compaction that best summarizes the original. This small compaction can be used to reconstruct the original texture or to re-synthesize new textures under user-supplied controls. More important, our technique allows real-time synthesis of globally varying textures on a GPU, where the texture memory is usually too small for large textures. We propose an optimization framework for inverse texture synthesis, ensuring that each input region is properly encoded in the output compaction. Our optimization process also automatically computes orientation fields for anisotropic textures containing both low- and high-frequency regions, a situation difficult to handle via existing techniques. © 2008 ACM.en_HK
dc.languageengen_US
dc.publisherAssociation for Computing Machinery, Incen_US
dc.relation.ispartofACM Transactions on Graphicsen_HK
dc.subjectGPU techniquesen_HK
dc.subjectTexture mappingen_HK
dc.subjectTexture synthesisen_HK
dc.titleInverse texture synthesisen_HK
dc.typeArticleen_HK
dc.identifier.emailWei, LY:lywei@cs.hku.hken_HK
dc.identifier.authorityWei, LY=rp01528en_HK
dc.description.naturelink_to_subscribed_fulltexten_US
dc.identifier.doi10.1145/1360612.1360651en_HK
dc.identifier.scopuseid_2-s2.0-49249139417en_HK
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-49249139417&selection=ref&src=s&origin=recordpageen_HK
dc.identifier.volume27en_HK
dc.identifier.issue3en_HK
dc.identifier.eissn1557-7368-
dc.identifier.isiWOS:000258262000041-
dc.publisher.placeUnited Statesen_HK
dc.identifier.scopusauthoridWei, LY=14523963300en_HK
dc.identifier.scopusauthoridHan, J=25824313600en_HK
dc.identifier.scopusauthoridZhou, K=7202915241en_HK
dc.identifier.scopusauthoridBao, H=7102201533en_HK
dc.identifier.scopusauthoridGuo, B=35248116900en_HK
dc.identifier.scopusauthoridShum, HY=7006094115en_HK
dc.identifier.citeulike3689894-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats