A Generative Model for Volume Rendering

We present a technique to synthesize and analyze volume-rendered images using generative models. We use the Generative Adversarial Network (GAN) framework to compute a model from a large collection of volume renderings, conditioned on (1) viewpoint and (2) transfer functions for opacity and color. O...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on visualization and computer graphics. - 1996. - 25(2019), 4 vom: 22. Apr., Seite 1636-1650
1. Verfasser: Berger, Matthew (VerfasserIn)
Weitere Verfasser: Li, Jixian, Levine, Joshua A
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2019
Zugriff auf das übergeordnete Werk:IEEE transactions on visualization and computer graphics
Schlagworte:Journal Article
LEADER 01000caa a22002652c 4500
001 NLM286363542
003 DE-627
005 20250223192100.0
007 cr uuu---uuuuu
008 231225s2019 xx |||||o 00| ||eng c
024 7 |a 10.1109/TVCG.2018.2816059  |2 doi 
028 5 2 |a pubmed25n0954.xml 
035 |a (DE-627)NLM286363542 
035 |a (NLM)29993811 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Berger, Matthew  |e verfasserin  |4 aut 
245 1 2 |a A Generative Model for Volume Rendering 
264 1 |c 2019 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Revised 20.11.2019 
500 |a published: Print-Electronic 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a We present a technique to synthesize and analyze volume-rendered images using generative models. We use the Generative Adversarial Network (GAN) framework to compute a model from a large collection of volume renderings, conditioned on (1) viewpoint and (2) transfer functions for opacity and color. Our approach facilitates tasks for volume analysis that are challenging to achieve using existing rendering techniques such as ray casting or texture-based methods. We show how to guide the user in transfer function editing by quantifying expected change in the output image. Additionally, the generative model transforms transfer functions into a view-invariant latent space specifically designed to synthesize volume-rendered images. We use this space directly for rendering, enabling the user to explore the space of volume-rendered images. As our model is independent of the choice of volume rendering process, we show how to analyze volume-rendered images produced by direct and global illumination lighting, for a variety of volume datasets 
650 4 |a Journal Article 
700 1 |a Li, Jixian  |e verfasserin  |4 aut 
700 1 |a Levine, Joshua A  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on visualization and computer graphics  |d 1996  |g 25(2019), 4 vom: 22. Apr., Seite 1636-1650  |w (DE-627)NLM098269445  |x 1941-0506  |7 nnas 
773 1 8 |g volume:25  |g year:2019  |g number:4  |g day:22  |g month:04  |g pages:1636-1650 
856 4 0 |u http://dx.doi.org/10.1109/TVCG.2018.2816059  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 25  |j 2019  |e 4  |b 22  |c 04  |h 1636-1650