cs.CVJul 15, 2026

DCVC-MB: Neural B-Frame Video Compression using State Space Models

Authors: Arjun AroraCalvin-Khang TaCarlos Restrepo-GaleanoKruthi MuraliNaga Akhil E SArunkumar MohananchettiarJay ShingalaTong Shao+2 more

Organizations: Dolby Laboratories · Voia · University of Delaware · Ittiam Systems

Abstract

In this paper we propose DCVC-Mamba (DCVC-MB), a neural video codec framework for B-frame coding. Our approach incorporates an IBP frame strategy for low-delay B-frame coding, a spatio-temporal fusion model based on state-space models for bidirectional temporal prediction, and an entropy-aware skipping mechanism that selectively omits coding certain latents to reduce entropy coding times. In addition to our model contributions we also implement two inference-time strategies that enhance compression performance. Experimental evaluation shows that DCVC-MB compares favorably to existing NVCs and traditional codecs. The method demonstrates BD-rate reductions of up to 8.98%8.98\% on average compared to prior neural video codecs, and improvements of up to 30.45%30.45\% and 1.81%1.81\% over the VTM-19.0-LDP and VTM-19.0-RA(Inter-GoP=16) benchmarks, respectively, contributing to advances in neural video compression.

Explore similar work

CardsList
  1. Ultra-Fast Neural Video Compression

    Jun 3, 2026Jiahao Li, Wenxuan Xie, Zhaoyang Jia +4Neural Video CodecsEncode