arXiv cs.CV
· Papers
DCVC-MB: Neural B-Frame Video Compression using State Space Models
arXiv:2607.14305v1 Announce Type: new 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