Binary-space-partitioned images for resolving image-based visibility

We propose a novel 2D representation for 3D visibility sorting, the Binary-Space-Partitioned Image (BSPI), to accelerate real-time image-based rendering. BSPI is an efficient 2D realization of a 3D BSP tree, which is commonly used in computer graphics for time-critical visibility sorting. Since the...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on visualization and computer graphics. - 1996. - 10(2004), 1 vom: 25. Jan., Seite 58-71
1. Verfasser: Fu, Chi-Wing (VerfasserIn)
Weitere Verfasser: Wong, Tien-Tsin, Tong, Wai-Shun, Tang, Chi-Keung, Hanson, Andrew J
Format: Aufsatz
Sprache:English
Veröffentlicht: 2004
Zugriff auf das übergeordnete Werk:IEEE transactions on visualization and computer graphics
Schlagworte:Evaluation Study Journal Article Research Support, Non-U.S. Gov't
LEADER 01000naa a22002652 4500
001 NLM150569246
003 DE-627
005 20231223054131.0
007 tu
008 231223s2004 xx ||||| 00| ||eng c
028 5 2 |a pubmed24n0502.xml 
035 |a (DE-627)NLM150569246 
035 |a (NLM)15382698 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Fu, Chi-Wing  |e verfasserin  |4 aut 
245 1 0 |a Binary-space-partitioned images for resolving image-based visibility 
264 1 |c 2004 
336 |a Text  |b txt  |2 rdacontent 
337 |a ohne Hilfsmittel zu benutzen  |b n  |2 rdamedia 
338 |a Band  |b nc  |2 rdacarrier 
500 |a Date Completed 19.10.2004 
500 |a Date Revised 10.12.2019 
500 |a published: Print 
500 |a Citation Status MEDLINE 
520 |a We propose a novel 2D representation for 3D visibility sorting, the Binary-Space-Partitioned Image (BSPI), to accelerate real-time image-based rendering. BSPI is an efficient 2D realization of a 3D BSP tree, which is commonly used in computer graphics for time-critical visibility sorting. Since the overall structure of a BSP tree is encoded in a BSPI, traversing a BSPI is comparable to traversing the corresponding BSP tree. BSPI performs visibility sorting efficiently and accurately in the 2D image space by warping the reference image triangle-by-triangle instead of pixel-by-pixel. Multiple BSPIs can be combined to solve "disocclusion," when an occluded portion of the scene becomes visible at a novel viewpoint. Our method is highly automatic, including a tensor voting preprocessing step that generates candidate image partition lines for BSPIs, filters the noisy input data by rejecting outliers, and interpolates missing information. Our system has been applied to a variety of real data, including stereo, motion, and range images 
650 4 |a Evaluation Study 
650 4 |a Journal Article 
650 4 |a Research Support, Non-U.S. Gov't 
700 1 |a Wong, Tien-Tsin  |e verfasserin  |4 aut 
700 1 |a Tong, Wai-Shun  |e verfasserin  |4 aut 
700 1 |a Tang, Chi-Keung  |e verfasserin  |4 aut 
700 1 |a Hanson, Andrew J  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on visualization and computer graphics  |d 1996  |g 10(2004), 1 vom: 25. Jan., Seite 58-71  |w (DE-627)NLM098269445  |x 1941-0506  |7 nnns 
773 1 8 |g volume:10  |g year:2004  |g number:1  |g day:25  |g month:01  |g pages:58-71 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 10  |j 2004  |e 1  |b 25  |c 01  |h 58-71