Switchable Motion Models for Non-Block-Based Inter Prediction in Learning-Based Video Coding

Brand F, Seiler J, Kaup A (2021)


Publication Type: Conference contribution, Conference Contribution

Publication year: 2021

Pages Range: 1-5

Event location: Bristol (Virtual)

DOI: 10.1109/pcs50896.2021.9477475

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.

Authors with CRIS profile

How to cite

APA:

Brand, F., Seiler, J., & Kaup, A. (2021). Switchable Motion Models for Non-Block-Based Inter Prediction in Learning-Based Video Coding. In Proceedings of the Picture Coding Symposium (PCS) (pp. 1-5). Bristol (Virtual).

MLA:

Brand, Fabian, Jürgen Seiler, and André Kaup. "Switchable Motion Models for Non-Block-Based Inter Prediction in Learning-Based Video Coding." Proceedings of the Picture Coding Symposium (PCS), Bristol (Virtual) 2021. 1-5.

BibTeX: Download