Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Liu, Yuxi, Jin, Dengchao, Huo, Shuai, Gu, Jiawen, Zhou, Chao, Bai, Huihui, Lu, Ming, Ma, Zhan
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2511.08938
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908647550877696
author Liu, Yuxi
Jin, Dengchao
Huo, Shuai
Gu, Jiawen
Zhou, Chao
Bai, Huihui
Lu, Ming
Ma, Zhan
author_facet Liu, Yuxi
Jin, Dengchao
Huo, Shuai
Gu, Jiawen
Zhou, Chao
Bai, Huihui
Lu, Ming
Ma, Zhan
contents Neural video compression (NVC) has made significant progress in recent years, while neural B-frame video compression (NBVC) remains underexplored compared to P-frame compression. NBVC can adopt bi-directional reference frames for better compression performance. However, NBVC's hierarchical coding may complicate continuous temporal prediction, especially at some hierarchical levels with a large frame span, which could cause the contribution of the two reference frames to be unbalanced. To optimize reference information utilization, we propose a novel NBVC method, termed Bi-directional Reference Harmonization Video Compression (BRHVC), with the proposed Bi-directional Motion Converge (BMC) and Bi-directional Contextual Fusion (BCF). BMC converges multiple optical flows in motion compression, leading to more accurate motion compensation on a larger scale. Then BCF explicitly models the weights of reference contexts under the guidance of motion compensation accuracy. With more efficient motions and contexts, BRHVC can effectively harmonize bi-directional references. Experimental results indicate that our BRHVC outperforms previous state-of-the-art NVC methods, even surpassing the traditional coding, VTM-RA (under random access configuration), on the HEVC datasets. The source code is released at https://github.com/kwai/NVC.
format Preprint
id arxiv_https___arxiv_org_abs_2511_08938
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Neural B-frame Video Compression with Bi-directional Reference Harmonization
Liu, Yuxi
Jin, Dengchao
Huo, Shuai
Gu, Jiawen
Zhou, Chao
Bai, Huihui
Lu, Ming
Ma, Zhan
Computer Vision and Pattern Recognition
Neural video compression (NVC) has made significant progress in recent years, while neural B-frame video compression (NBVC) remains underexplored compared to P-frame compression. NBVC can adopt bi-directional reference frames for better compression performance. However, NBVC's hierarchical coding may complicate continuous temporal prediction, especially at some hierarchical levels with a large frame span, which could cause the contribution of the two reference frames to be unbalanced. To optimize reference information utilization, we propose a novel NBVC method, termed Bi-directional Reference Harmonization Video Compression (BRHVC), with the proposed Bi-directional Motion Converge (BMC) and Bi-directional Contextual Fusion (BCF). BMC converges multiple optical flows in motion compression, leading to more accurate motion compensation on a larger scale. Then BCF explicitly models the weights of reference contexts under the guidance of motion compensation accuracy. With more efficient motions and contexts, BRHVC can effectively harmonize bi-directional references. Experimental results indicate that our BRHVC outperforms previous state-of-the-art NVC methods, even surpassing the traditional coding, VTM-RA (under random access configuration), on the HEVC datasets. The source code is released at https://github.com/kwai/NVC.
title Neural B-frame Video Compression with Bi-directional Reference Harmonization
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.08938