Jump to content

View synthesis

From Wikipedia, the free encyclopedia

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][2]

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 view point television. The technique has also been applied to real-estate marketing, where novel views of a listing's interior are generated from a limited set of photographs for use in virtual home staging.[3][4]

See also

[edit]

References

[edit]
  1. ^ "Velasco, Jose Maria", Benezit Dictionary of Artists, Oxford University Press, 2011-10-31, doi:10.1093/benz/9780199773787.article.b00189225
  2. ^ MultiDiff: Consistent Novel View Synthesis from a Single Image. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2024.
  3. ^ Dan, T. (2025). Generation and Synthesis of Video from Static Images for Real Estate Virtual Tours. 24th RoEduNet Conference: Networking in Education and Research.
  4. ^ "AI-based MLS virtual staging workflow and multi-view consistency". Edensign. October 20, 2025. Retrieved 2026-05-26.
[edit]