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

• URL: http://arxiv.org/abs/2607.14305v1
• Date: Wed, 15 Jul 2026 19:09:24 GMT
• Title: DCVC-MB: Neural B-Frame Video Compression using State Space Models
• Abstract summary: We propose DCVC-MB, a neural video framework for B-frame coding.<n>We show that DCVC-MB compares favorably to existing NVCs and traditional codecs.
• Score: 5.73742794192395
• License: http://creativecommons.org/licenses/by/4.0/
• 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 $8.98\%$ on average compared to prior neural video codecs, and improvements of up to $30.45\%$ and $1.81\%$ over the VTM-19.0-LDP and VTM-19.0-RA(Inter-GoP=16) benchmarks, respectively, contributing to advances in neural video compression.

Related papers

• ZeroGVC: Zero-Shot Generative Video Compression with Autoregressive Diffusion Priors [52.50325804778549]
  We propose ZeroGVC, a zero-shot generative video compression framework.<n>ZeroGVC encodes the first frame of each group of pictures (GOP) with an image and represents subsequent P-frames through Codebook-Guided Autoregressive Latent Compression.<n>Experiments on standard video compression benchmarks demonstrate that ZeroGVC achieves superior perceptual reconstruction quality at ultra-lows without any additional training.
  arXiv  Detail & Related papers  (2026-06-21T07:46:14Z)
• Neural B-frame Video Compression with Bi-directional Reference Harmonization [50.067848395760755]
  We propose a novel neural B-frame video compression method, Bi-directional Reference Harmonization Video Compression (BRHVC)<n>BRHVC uses Bi-directional Motion Converge (BMC) and Bi-directional Contextual Fusion (BCF) to optimize reference information utilization.<n> Experimental results indicate that our BRHVC outperforms previous state-of-the-art NVC methods.
  arXiv  Detail & Related papers  (2025-11-12T03:30:37Z)
• Real-Time Neural Video Compression with Unified Intra and Inter Coding [8.998142257336674]
  We present an NVC framework with unified intra and inter coding, where every frame is processed by a single model.<n>We propose a simultaneous two-frame compression design to exploit interframe redundancy not only forwardly but also backwardly.<n>Our scheme outperforms DCVC-RT by an average of 12.1% BD-rate reduction, delivers more stable and quality per frame, and retains real-time encoding/decoding performances.
  arXiv  Detail & Related papers  (2025-10-16T08:31:44Z)
• Towards Practical Real-Time Neural Video Compression [60.390180067626396]
  We introduce a practical real-time neural video (NVC) designed to deliver high compression ratio, low latency and broad versatility.<n>Experiments show our proposed DCVC-RT achieves an impressive average encoding/desampling speed 125.2/112.8 (frames per second) for 1080p video, while saving an average of 21% in fps compared to H.266/VTM.
  arXiv  Detail & Related papers  (2025-02-28T06:32:23Z)
• Bi-Directional Deep Contextual Video Compression [17.195099321371526]
  We introduce a bi-directional deep contextual video compression scheme tailored for B-frames, termed DCVC-B.<n>First, we develop a bi-directional motion difference context propagation method for effective motion difference coding.<n>Second, we propose a bi-directional contextual compression model and a corresponding bi-directional temporal entropy model.<n>Third, we propose a hierarchical quality structure-based training strategy, leading to an effective bit allocation across large groups of pictures.
  arXiv  Detail & Related papers  (2024-08-16T08:45:25Z)
• IBVC: Interpolation-driven B-frame Video Compression [68.18440522300536]
  B-frame video compression aims to adopt bi-directional motion estimation and motion compensation (MEMC) coding for middle frame reconstruction. Previous learned approaches often directly extend neural P-frame codecs to B-frame relying on bi-directional optical-flow estimation. We propose a simple yet effective structure called Interpolation-B-frame Video Compression (IBVC) to address these issues.
  arXiv  Detail & Related papers  (2023-09-25T02:45:51Z)
• Neural Video Compression with Temporal Layer-Adaptive Hierarchical B-frame Coding [5.8550373172233305]
  We propose an NVC model exploiting hierarchical B-frame coding with temporal layer-adaptive optimization. The model achieves an impressive BD-rate gain of -39.86% against the baseline. It also resolves the challenges in sequences with large or complex motions with up to -49.13% more BD-rate gains than the simple bidirectional extension.
  arXiv  Detail & Related papers  (2023-08-30T06:49:34Z)
• Conditional Entropy Coding for Efficient Video Compression [82.35389813794372]
  We propose a very simple and efficient video compression framework that only focuses on modeling the conditional entropy between frames. We first show that a simple architecture modeling the entropy between the image latent codes is as competitive as other neural video compression works and video codecs. We then propose a novel internal learning extension on top of this architecture that brings an additional 10% savings without trading off decoding speed.
  arXiv  Detail & Related papers  (2020-08-20T20:01:59Z)
• Learning for Video Compression with Recurrent Auto-Encoder and Recurrent Probability Model [164.7489982837475]
  This paper proposes a Recurrent Learned Video Compression (RLVC) approach with the Recurrent Auto-Encoder (RAE) and Recurrent Probability Model ( RPM) The RAE employs recurrent cells in both the encoder and decoder to exploit the temporal correlation among video frames. Our approach achieves the state-of-the-art learned video compression performance in terms of both PSNR and MS-SSIM.
  arXiv  Detail & Related papers  (2020-06-24T08:46:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.