View synthesis

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.

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

• 3D reconstruction from multiple images
• Image-based modeling and rendering
• Image synthesis

External links

• Shuai Li; Ce Zhu; Ming-Ting Sun (2018). "Hole Filling with Multiple Reference Views in DIBR View Synthesis". IEEE Transactions on Multimedia. 20 (8): 1948–1959. arXiv:1802.03079. Bibcode:2018arXiv180203079L. doi:10.1109/TMM.2018.2791810. S2CID 33449031.
• Ce Zhu; Shuai Li (2016). "Depth Image Based View Synthesis: New Insights and Perspectives on Hole Generation and Filling". IEEE Transactions on Broadcasting. 62 (1): 82–93. doi:10.1109/TBC.2015.2475697. S2CID 19100077.
• Mansi Sharma; Santanu Chaudhury; Brejesh Lall (2014). Kinect-Variety Fusion: A Novel Hybrid Approach for Artifacts-Free 3DTV Content Generation. In 22nd International Conference on Pattern Recognition (ICPR), Stockholm, 2014. doi:10.1109/ICPR.2014.395.
• http://news.bbc.co.uk/1/hi/technology/3833831.stm
• https://web.archive.org/web/20060905013927/http://www.cs.wisc.edu/computer-vision/projects/interp/interp.html
• http://homepages.inf.ed.ac.uk/rbf/CVonline/LOCAL_COPIES/FUSIELLO4/tutorial.html#x1-10001
• https://web.archive.org/web/20061126225514/http://www-sop.inria.fr/robotvis/personnel/fabad/PhD/index.html
• http://www.cs.huji.ac.il/labs/vision/demos/synthesis/synthesis.html
• http://www.hpl.hp.com/research/mmsl/projects/graphics/chromaglyph/index.html