Residual frame
From HandWiki - Reading time: 2 min
In video compression algorithms a residual frame is formed by subtracting the reference frame from the desired frame. This difference is known as the error or residual frame. The residual frame normally has less information entropy, due to nearby video frames having similarities, and therefore requires fewer bits to compress.[1]
An encoder will use various algorithms such as motion estimation to construct a frame that describes the differences. This allows a decoder to use the reference frame plus the differences to construct the desired frame.[1]
Recent improvements have led to "better action recognition."[2]
See also
References
- ↑ 1.0 1.1 Richardson, Iain E. (2004). H.264 and MPEG-4 Video Compression: Video Coding for Next-generation Multimedia. Wiley. pp. 29–30, 40, 260. ISBN 9780470869604. https://books.google.com/books?id=n9YVhx2zgz4C&dq=%22Residual+frame%22+-wikipedia&pg=PA30. Retrieved November 19, 2025.
- ↑ Tao, Li; Wang, Xueting; Yamasaki, Toshihiko (16 January 2020). "Rethinking Motion Representation: Residual Frames with 3D ConvNets for Better Action Recognition". arXiv:2001.05661 [cs.CV].
 |  |
Licensed under CC BY-SA 3.0 | Source: https://handwiki.org/wiki/Residual_frame17 views | ↧ Download this article as ZWI file
EncycloReader
is supported by the 
KSF