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 convolutional neural network (CNN) architecture that processes the basic block-based motion-compensated prediction of the current frame as well as predictions from past reference frames. This method allows to reduce typical artifacts such as blockiness, and achieves a more accurate prediction of motion thanks to the representation capabilities of CNNs, leading to smaller prediction residuals. Preliminary results show that the proposed approach is capable of providing BD-rate gains up to 6%.
Deep Multiframe Enhancement for Motion Prediction in Video Compression
2021-01-01
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
DDC: | 629 |
Multiframe Structure from Motion in Perspective
British Library Conference Proceedings | 1995
|Dealing with Noise in Multiframe Structure from Motion
British Library Online Contents | 1999
|Multiframe Motion Segmentation with Missing Data Using PowerFactorization and GPCA
British Library Online Contents | 2008
|Multiframe detector/tracker: optimal performance
IEEE | 2001
|Fast multiframe selection algorithm based on spatial-temporal characteristics of motion field
British Library Online Contents | 2008
|