Deep motion estimation for parallel inter-frame prediction in video compression

Standard video codecs rely on optical flow to guide inter-frame prediction: pixels from reference frames are moved via motion vectors to predict target video frames. We propose to learn binary motion codes that are encoded based on an input video sequence. These codes are not limited to 2D translati...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2019-12
Main Authors: Nortje, André, Engelbrecht, Herman A, Kamper, Herman
Format: Article
Language:English
Subjects:
Algorithms
Binary codes
Codec
Decoding
Motion simulation
Neural networks
Occlusion
Optical flow (image analysis)
Translations
Video compression
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Standard video codecs rely on optical flow to guide inter-frame prediction: pixels from reference frames are moved via motion vectors to predict target video frames. We propose to learn binary motion codes that are encoded based on an input video sequence. These codes are not limited to 2D translations, but can capture complex motion (warping, rotation and occlusion). Our motion codes are learned as part of a single neural network which also learns to compress and decode them. This approach supports parallel video frame decoding instead of the sequential motion estimation and compensation of flow-based methods. We also introduce 3D dynamic bit assignment to adapt to object displacements caused by motion, yielding additional bit savings. By replacing the optical flow-based block-motion algorithms found in an existing video codec with our learned inter-frame prediction model, our approach outperforms the standard H.264 and H.265 video codecs across at low bitrates.
ISSN:2331-8422