FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W156767426> ?p ?o ?g. }

• W156767426 abstract "Texture synthesis has always been an interesting research topic in Graphics. Neighborhood-based algorithms have two common stages: search for most similar neighborhoods in the sample texture; merge a local neighborhood into the (partially) synthesized output texture. When the first stage can not find good neighbors, the second stage may generate seams. We propose to extract a feature map from the input texture and synthesize a feature map for output. We develop novel algorithms to perform feature matching and alignment. This approach significantly reduces feature discontinuities and related artifacts. For 3D surfaces, things get more complicated as continuity constraints restrict the variability of synthesized textures. We propose to relax the restrictions and decompose synthesis into two stages: feature map synthesis and Laplacian texture reconstruction. Experiments indicate that this relaxation can produce desirable results for regular texture synthesis as well as texture mixing from multiple sources. Visual data approximation is another important issue in Graphics. We propose hierarchical tensor approximation to expose multi-scale and inhomogeneous structures in visual datasets. The blocks on each level in the hierarchy are pruned and approximated as a tensor ensemble, and residual tensors are subdivided to form the next level in the hierarchy. Experiments prove that the hierarchical multilinear models can achieve higher compression ratios and quality on high-dimensional visual data than wavelet (packet) transforms and single-level tensor approximation. Finally, we propose to apply multilinear models to wavelet domain to reduce overhead. High-frequency wavelet sub-bands are subdivided into small blocks most of which get pruned. The blocks are usually correlated especially when properly classified. Different channels and sub-bands may exhibit strong redundancy as well. We reorganize the subdivided blocks into small tensors, classify the unpruned ones and approximate each cluster as a tensor ensemble. Experiments on images and medical volume data indicate that this approach achieves better approximation quality than wavelet (packet) transforms and hybrid linear models." @default.
• W156767426 created "2016-06-24" @default.
• W156767426 creator A5071959906 @default.
• W156767426 creator A5087152421 @default.
• W156767426 date "2007-01-01" @default.
• W156767426 modified "2023-09-23" @default.
• W156767426 title "Feature-based texture synthesis and hierarchical tensor approximation" @default.
• W156767426 cites W1485280399 @default.
• W156767426 cites W1514814671 @default.
• W156767426 cites W1520618957 @default.
• W156767426 cites W1526371894 @default.
• W156767426 cites W1540859741 @default.
• W156767426 cites W1594957066 @default.
• W156767426 cites W1760895834 @default.
• W156767426 cites W1902027874 @default.
• W156767426 cites W1909138541 @default.
• W156767426 cites W1964673636 @default.
• W156767426 cites W1967577110 @default.
• W156767426 cites W1974879594 @default.
• W156767426 cites W1975006305 @default.
• W156767426 cites W1991042426 @default.
• W156767426 cites W1997108785 @default.
• W156767426 cites W1999360130 @default.
• W156767426 cites W2000123870 @default.
• W156767426 cites W2002598080 @default.
• W156767426 cites W2004473561 @default.
• W156767426 cites W2012332472 @default.
• W156767426 cites W2013912476 @default.
• W156767426 cites W2018282388 @default.
• W156767426 cites W2018419001 @default.
• W156767426 cites W2026517469 @default.
• W156767426 cites W2029248817 @default.
• W156767426 cites W2036750154 @default.
• W156767426 cites W2042371054 @default.
• W156767426 cites W2049633694 @default.
• W156767426 cites W2053691921 @default.
• W156767426 cites W2066462711 @default.
• W156767426 cites W2068623560 @default.
• W156767426 cites W2069912449 @default.
• W156767426 cites W2070604790 @default.
• W156767426 cites W2077786999 @default.
• W156767426 cites W2078790577 @default.
• W156767426 cites W2083518538 @default.
• W156767426 cites W2085990730 @default.
• W156767426 cites W2097543505 @default.
• W156767426 cites W2101419919 @default.
• W156767426 cites W2101789093 @default.
• W156767426 cites W2109504624 @default.
• W156767426 cites W2112328859 @default.
• W156767426 cites W2113055885 @default.
• W156767426 cites W2116013899 @default.
• W156767426 cites W2117853853 @default.
• W156767426 cites W2125742596 @default.
• W156767426 cites W2125771762 @default.
• W156767426 cites W2128574158 @default.
• W156767426 cites W2128944356 @default.
• W156767426 cites W2132896093 @default.
• W156767426 cites W2135666716 @default.
• W156767426 cites W2136762275 @default.
• W156767426 cites W2139796514 @default.
• W156767426 cites W2145023731 @default.
• W156767426 cites W2146278756 @default.
• W156767426 cites W2146766088 @default.
• W156767426 cites W2147555557 @default.
• W156767426 cites W2148593155 @default.
• W156767426 cites W2149521538 @default.
• W156767426 cites W2149774527 @default.
• W156767426 cites W2151035455 @default.
• W156767426 cites W2151406969 @default.
• W156767426 cites W2153663612 @default.
• W156767426 cites W2153763188 @default.
• W156767426 cites W2156041358 @default.
• W156767426 cites W2157009172 @default.
• W156767426 cites W2158778494 @default.
• W156767426 cites W2163318306 @default.
• W156767426 cites W2164369380 @default.
• W156767426 cites W2166087152 @default.
• W156767426 cites W2166956700 @default.
• W156767426 cites W2167372553 @default.
• W156767426 cites W2232702494 @default.
• W156767426 cites W2249587656 @default.
• W156767426 cites W2292976057 @default.
• W156767426 cites W2295660824 @default.
• W156767426 cites W2798909945 @default.
• W156767426 cites W2998023265 @default.
• W156767426 cites W56210758 @default.
• W156767426 hasPublicationYear "2007" @default.
• W156767426 type Work @default.
• W156767426 sameAs 156767426 @default.
• W156767426 citedByCount "0" @default.
• W156767426 crossrefType "journal-article" @default.
• W156767426 hasAuthorship W156767426A5071959906 @default.
• W156767426 hasAuthorship W156767426A5087152421 @default.
• W156767426 hasConcept C11413529 @default.
• W156767426 hasConcept C115961682 @default.
• W156767426 hasConcept C138885662 @default.
• W156767426 hasConcept C144743038 @default.
• W156767426 hasConcept C153180895 @default.
• W156767426 hasConcept C154945302 @default.
• W156767426 hasConcept C155281189 @default.

• next