東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Feature-based texture synthesis and ...

Wu, Qing.

FindBook

Google Book

Amazon

博客來

Feature-based texture synthesis and hierarchical tensor approximation.

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Feature-based texture synthesis and hierarchical tensor approximation./
作者:	Wu, Qing.
面頁冊數:	80 p.
附註:	Adviser: Yizhou Yu.
Contained By:	Dissertation Abstracts International69-02B.
標題:	Computer Science. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3301250
ISBN:	9780549463689

Feature-based texture synthesis and hierarchical tensor approximation.
Wu, Qing.

Feature-based texture synthesis and hierarchical tensor approximation. - 80 p.

Adviser: Yizhou Yu.

Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 2007.

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.

ISBN: 9780549463689Subjects--Topical Terms:

626642
Computer Science.

Feature-based texture synthesis and hierarchical tensor approximation.
LDR:03117nam 2200301 a 45 001 939140
005 20110512
008 110512s2007 ||||||||||||||||| ||eng d
020 $a 9780549463689
035 $a (UMI)AAI3301250
035 $a AAI3301250
040 $a UMI $c UMI
100 1 $a Wu, Qing. $3 1263132
245 1 0 $a Feature-based texture synthesis and hierarchical tensor approximation.
300 $a 80 p.
500 $a Adviser: Yizhou Yu.
500 $a Source: Dissertation Abstracts International, Volume: 69-02, Section: B, page: 1123.
502 $a Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 2007.
520 $a 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.
520 $a 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.
520 $a 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.
520 $a 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.
590 $a School code: 0090.
650 4 $a Computer Science. $3 626642
690 $a 0984
710 2 $a University of Illinois at Urbana-Champaign. $3 626646
773 0 $t Dissertation Abstracts International $g 69-02B.
790 $a 0090
790 1 0 $a Yu, Yizhou, $e advisor
791 $a Ph.D.
792 $a 2007
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3301250