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.
@article{arxiv.2511.01590,
title = {EV-NVC: Efficient Variable bitrate Neural Video Compression},
author = {Yongcun Hu and Yingzhen Zhai and Jixiang Luo and Wenrui Dai and Dell Zhang and Hongkai Xiong and Xuelong Li},
journal= {arXiv preprint arXiv:2511.01590},
year = {2025}
}