Jump to content

View synthesis: Difference between revisions

From Wikipedia, the free encyclopedia
Content deleted Content added
m References
Bebdt (talk | contribs)
m Grammatical details
Line 1: Line 1:
In [[computer graphics]], '''view synthesis''', or '''novel view synthesis''', is a task which consists of generating images of a specific subject or scene from a specific point of view, when the only available information are pictures taken from different point of views.<ref>{{Citation |title=Velasco, Jose Maria |date=2011-10-31 |work=Benezit Dictionary of Artists |url=http://dx.doi.org/10.1093/benz/9780199773787.article.b00189225 |doi=10.1093/benz/9780199773787.article.b00189225 |access-date=2024-03-31 |publisher=Oxford University Press}}</ref>
In [[computer graphics]], '''view synthesis''', or '''novel view synthesis''', is a task which consists of generating images of a specific subject or scene from a specific point of view, when the only available information is pictures taken from different points of view.<ref>{{Citation |title=Velasco, Jose Maria |date=2011-10-31 |work=Benezit Dictionary of Artists |url=http://dx.doi.org/10.1093/benz/9780199773787.article.b00189225 |doi=10.1093/benz/9780199773787.article.b00189225 |access-date=2024-03-31 |publisher=Oxford University Press}}</ref>


Such task was only recently (late 2010s - early 2020s) tackled with significative success, mostly as a result of advances in [[machine learning]]. Notable successful methods are [[Neural radiance field]]s, and 3D [[gaussian splatting]].
This task was only recently (late 2010s - early 2020s) tackled with significant success, mostly as a result of advances in [[machine learning]]. Notable successful methods are [[Neural radiance field]]s, and 3D [[gaussian splatting]].


Applications of view synthesis are numerous, one of them being [[Free view point television|Free viewpoint television]].
Applications of view synthesis are numerous, one of them being [[Free view point television|Free viewpoint television]].

Revision as of 15:57, 18 May 2024

In computer graphics, view synthesis, or novel view synthesis, is a task which consists of generating images of a specific subject or scene from a specific point of view, when the only available information is pictures taken from different points of view.[1]

This task was only recently (late 2010s - early 2020s) tackled with significant success, mostly as a result of advances in machine learning. Notable successful methods are Neural radiance fields, and 3D gaussian splatting.

Applications of view synthesis are numerous, one of them being Free viewpoint television.

See also

References

  1. ^ "Velasco, Jose Maria", Benezit Dictionary of Artists, Oxford University Press, 2011-10-31, doi:10.1093/benz/9780199773787.article.b00189225, retrieved 2024-03-31