Title | ||
---|---|---|
Switchable Motion Models for Non-Block-Based Inter Prediction in Learning-Based Video Coding |
Abstract | ||
---|---|---|
Most state-of-the-art video coders rely on a block structure. For inter-frame prediction, motion vectors are transmitted per block. For example in VVC, the coder can choose between a translational or an affine motion model on a block level, depending on the content. In non-block-based coding, which is on the rise since the development of end-to-end learning based image compression, the motion vectors have to be transmitted differently. Due to the missing inherent block structure, switching between different motion models presents a challenge, but also an opportunity. In this paper, we propose an alternative approach to efficiently signal additional information regarding the motion model to improve the quality of the motion compensated image. Using our methods, we are able to increase the quality of the prediction image in our scenario by 0.40 dB on average and by up to 0.88 dB for sequences with strong and complex motion at the same rate. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/PCS50896.2021.9477475 | 2021 Picture Coding Symposium (PCS) |
Keywords | DocType | ISSN |
switchable motion models,nonblock-based inter prediction,learning-based video coding,state-of-the-art video coders,interframe prediction,motion vectors,coder,affine motion model,block level,nonblock-based coding,end-to-end learning based image compression,missing inherent block structure,motion models,motion compensated image,prediction image,strong motion,complex motion,VVC | Conference | 2330-7935 |
ISBN | Citations | PageRank |
978-1-6654-3078-4 | 0 | 0.34 |
References | Authors | |
0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Fabian Brand | 1 | 1 | 3.74 |
Jürgen Seiler | 2 | 145 | 28.28 |
André Kaup | 3 | 0 | 0.34 |