Self-Supervised Learning of Perceptually Optimized Block Motion Estimates for Video Compression

Block based motion estimation is integral to inter prediction processes performed in hybrid video codecs. Prevalent block matching based methods that are used to compute block motion vectors (MVs) rely on computationally intensive search procedures. They also suffer from the aperture problem, which...

Full description

Saved in:

Bibliographic Details
Published in:	IEEE transactions on image processing Vol. 32; p. 1
Main Authors:	Paul, Somdyuti, Norkin, Andrey, Bovik, Alan C.
Format:	Journal Article
Language:	English
Published:	United States IEEE 01.01.2023 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:	Algorithms Artificial neural networks AV1 Block motion estimation Codec Coders Computational modeling convolutional neural networks Estimation Frames (data processing) Image coding inter prediction Machine learning Matching Motion estimation Motion simulation motion vectors Performance prediction Predictive models Quality assessment Self-supervised learning Video compression Visualization
ISSN:	1057-7149, 1941-0042, 1941-0042
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Be the first to leave a comment!