EV-NVC: Efficient Variable bitrate Neural Video Compression

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Hu, Yongcun, Zhai, Yingzhen, Luo, Jixiang, Dai, Wenrui, Zhang, Dell, Xiong, Hongkai, Li, Xuelong
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909884342075392
author Hu, Yongcun
Zhai, Yingzhen
Luo, Jixiang
Dai, Wenrui
Zhang, Dell
Xiong, Hongkai
Li, Xuelong
author_facet Hu, Yongcun
Zhai, Yingzhen
Luo, Jixiang
Dai, Wenrui
Zhang, Dell
Xiong, Hongkai
Li, Xuelong
contents Training neural video codec (NVC) with variable rate is a highly challenging task due to its complex training strategies and model structure. In this paper, we train an efficient variable bitrate neural video codec (EV-NVC) with the piecewise linear sampler (PLS) to improve the rate-distortion performance in high bitrate range, and the long-short-term feature fusion module (LSTFFM) to enhance the context modeling. Besides, we introduce mixed-precision training and discuss the different training strategies for each stage in detail to fully evaluate its effectiveness. Experimental results show that our approach reduces the BD-rate by 30.56% compared to HM-16.25 within low-delay mode.
format Preprint
id arxiv_https___arxiv_org_abs_2511_01590
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle EV-NVC: Efficient Variable bitrate Neural Video Compression
Hu, Yongcun
Zhai, Yingzhen
Luo, Jixiang
Dai, Wenrui
Zhang, Dell
Xiong, Hongkai
Li, Xuelong
Multimedia
Training neural video codec (NVC) with variable rate is a highly challenging task due to its complex training strategies and model structure. In this paper, we train an efficient variable bitrate neural video codec (EV-NVC) with the piecewise linear sampler (PLS) to improve the rate-distortion performance in high bitrate range, and the long-short-term feature fusion module (LSTFFM) to enhance the context modeling. Besides, we introduce mixed-precision training and discuss the different training strategies for each stage in detail to fully evaluate its effectiveness. Experimental results show that our approach reduces the BD-rate by 30.56% compared to HM-16.25 within low-delay mode.
title EV-NVC: Efficient Variable bitrate Neural Video Compression
topic Multimedia
url https://arxiv.org/abs/2511.01590