Abstract | ||
---|---|---|
This work proposes a novel Deep Learning technique to increase the efficiency of currently available video compression techniques based on motion compensation. The goal is to improve the frame prediction task, whereby a more accurate prediction of the motion from the reference frames to the target frame allows to reduce the rate needed to encode the residual. This is achieved by means of a convolu... |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/ICECS53924.2021.9665523 | 2021 28th IEEE International Conference on Electronics, Circuits, and Systems (ICECS) |
Keywords | DocType | ISBN |
Motion estimation,Refining,Video compression,Predictive models,Network architecture,Motion compensation,Encoding | Conference | 978-1-7281-8281-0 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Nicola Prette | 1 | 0 | 0.34 |
Diego Valsesia | 2 | 0 | 0.34 |
Tiziano Bianchi | 3 | 1003 | 62.55 |