Hybrid Local-Global Context Learning for Neural Video Compression

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhai, Yongqi, Yang, Jiayu, Jiang, Wei, Yang, Chunhui, Tang, Luyang, Wang, Ronggang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913592061722624
author Zhai, Yongqi
Yang, Jiayu
Jiang, Wei
Yang, Chunhui
Tang, Luyang
Wang, Ronggang
author_facet Zhai, Yongqi
Yang, Jiayu
Jiang, Wei
Yang, Chunhui
Tang, Luyang
Wang, Ronggang
contents In neural video codecs, current state-of-the-art methods typically adopt multi-scale motion compensation to handle diverse motions. These methods estimate and compress either optical flow or deformable offsets to reduce inter-frame redundancy. However, flow-based methods often suffer from inaccurate motion estimation in complicated scenes. Deformable convolution-based methods are more robust but have a higher bit cost for motion coding. In this paper, we propose a hybrid context generation module, which combines the advantages of the above methods in an optimal way and achieves accurate compensation at a low bit cost. Specifically, considering the characteristics of features at different scales, we adopt flow-guided deformable compensation at largest-scale to produce accurate alignment in detailed regions. For smaller-scale features, we perform flow-based warping to save the bit cost for motion coding. Furthermore, we design a local-global context enhancement module to fully explore the local-global information of previous reconstructed signals. Experimental results demonstrate that our proposed Hybrid Local-Global Context learning (HLGC) method can significantly enhance the state-of-the-art methods on standard test datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2412_00446
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Hybrid Local-Global Context Learning for Neural Video Compression
Zhai, Yongqi
Yang, Jiayu
Jiang, Wei
Yang, Chunhui
Tang, Luyang
Wang, Ronggang
Multimedia
Computer Vision and Pattern Recognition
In neural video codecs, current state-of-the-art methods typically adopt multi-scale motion compensation to handle diverse motions. These methods estimate and compress either optical flow or deformable offsets to reduce inter-frame redundancy. However, flow-based methods often suffer from inaccurate motion estimation in complicated scenes. Deformable convolution-based methods are more robust but have a higher bit cost for motion coding. In this paper, we propose a hybrid context generation module, which combines the advantages of the above methods in an optimal way and achieves accurate compensation at a low bit cost. Specifically, considering the characteristics of features at different scales, we adopt flow-guided deformable compensation at largest-scale to produce accurate alignment in detailed regions. For smaller-scale features, we perform flow-based warping to save the bit cost for motion coding. Furthermore, we design a local-global context enhancement module to fully explore the local-global information of previous reconstructed signals. Experimental results demonstrate that our proposed Hybrid Local-Global Context learning (HLGC) method can significantly enhance the state-of-the-art methods on standard test datasets.
title Hybrid Local-Global Context Learning for Neural Video Compression
topic Multimedia
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.00446