{"ID":2846706,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.01590","arxiv_id":"2511.01590","title":"EV-NVC: Efficient Variable bitrate Neural Video Compression","abstract":"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.","short_abstract":"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 bitra...","url_abs":"https://arxiv.org/abs/2511.01590","url_pdf":"https://arxiv.org/pdf/2511.01590v1","authors":"[\"Yongcun Hu\",\"Yingzhen Zhai\",\"Jixiang Luo\",\"Wenrui Dai\",\"Dell Zhang\",\"Hongkai Xiong\",\"Xuelong Li\"]","published":"2025-11-03T13:57:25Z","proceeding":"cs.MM","tasks":"[\"cs.MM\"]","methods":"[]","has_code":false}