Efficient Sub-pixel Motion Compensation in Learned Video Codecs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ladune, Théo, Leguay, Thomas, Philippe, Pierrick, Clare, Gordon, Henry, Félix
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911170841018368
author Ladune, Théo
Leguay, Thomas
Philippe, Pierrick
Clare, Gordon
Henry, Félix
author_facet Ladune, Théo
Leguay, Thomas
Philippe, Pierrick
Clare, Gordon
Henry, Félix
contents Motion compensation is a key component of video codecs. Conventional codecs (HEVC and VVC) have carefully refined this coding step, with an important focus on sub-pixel motion compensation. On the other hand, learned codecs achieve sub-pixel motion compensation through simple bilinear filtering. This paper offers to improve learned codec motion compensation by drawing inspiration from conventional codecs. It is shown that the usage of more advanced interpolation filters, block-based motion information and finite motion accuracy lead to better compression performance and lower decoding complexity. Experimental results are provided on the Cool-chic video codec, where we demonstrate a rate decrease of more than 10% and a lowering of motion-related decoding complexity from 391 MAC per pixel to 214 MAC per pixel. All contributions are made open-source at https://github.com/Orange-OpenSource/Cool-Chic
format Preprint
id arxiv_https___arxiv_org_abs_2507_21926
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Efficient Sub-pixel Motion Compensation in Learned Video Codecs
Ladune, Théo
Leguay, Thomas
Philippe, Pierrick
Clare, Gordon
Henry, Félix
Multimedia
Image and Video Processing
Motion compensation is a key component of video codecs. Conventional codecs (HEVC and VVC) have carefully refined this coding step, with an important focus on sub-pixel motion compensation. On the other hand, learned codecs achieve sub-pixel motion compensation through simple bilinear filtering. This paper offers to improve learned codec motion compensation by drawing inspiration from conventional codecs. It is shown that the usage of more advanced interpolation filters, block-based motion information and finite motion accuracy lead to better compression performance and lower decoding complexity. Experimental results are provided on the Cool-chic video codec, where we demonstrate a rate decrease of more than 10% and a lowering of motion-related decoding complexity from 391 MAC per pixel to 214 MAC per pixel. All contributions are made open-source at https://github.com/Orange-OpenSource/Cool-Chic
title Efficient Sub-pixel Motion Compensation in Learned Video Codecs
topic Multimedia
Image and Video Processing
url https://arxiv.org/abs/2507.21926