{"ID":2842587,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.08938","arxiv_id":"2511.08938","title":"Neural B-frame Video Compression with Bi-directional Reference Harmonization","abstract":"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.","short_abstract":"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 continu...","url_abs":"https://arxiv.org/abs/2511.08938","url_pdf":"https://arxiv.org/pdf/2511.08938v1","authors":"[\"Yuxi Liu\",\"Dengchao Jin\",\"Shuai Huo\",\"Jiawen Gu\",\"Chao Zhou\",\"Huihui Bai\",\"Ming Lu\",\"Zhan Ma\"]","published":"2025-11-12T03:30:37Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":607139,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2842587,"paper_url":"https://arxiv.org/abs/2511.08938","paper_title":"Neural B-frame Video Compression with Bi-directional Reference Harmonization","repo_url":"https://github.com/kwai/NVC","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}