DCVC-MB：使用状态空间模型的神经B帧视频压缩
DCVC-MB: Neural B-Frame Video Compression using State Space Models
浏览论文内容
中文总结 AI 辅助
提出用于B帧编码的神经视频编解码框架DCVC-MB，采用IBP帧策略、时空融合模型和熵感知跳过机制，还有两种推理时策略增强压缩性能，实验表明其优于现有编解码器，推动神经视频压缩发展。
中文摘要 AI 辅助
本文提出了DCVC-Mamba（DCVC-MB），一种用于B帧编码的神经视频编解码框架。我们的方法包括用于低延迟B帧编码的IBP帧策略、基于状态空间模型的时空融合模型用于双向时间预测，以及一种熵感知跳过机制，选择性地省略某些潜在编码以减少熵编码次数。除了模型贡献，还实现了两种推理时策略来增强压缩性能。实验评估表明DCVC-MB优于现有神经视频编解码器和传统编解码器，平均BD率比之前的神经视频编解码器降低高达8.98%，比VTM-19.0-LDP和VTM-19.0-RA（Inter-GoP=16）基准分别提高高达30.45%和1.81%，推动了神经视频压缩的发展。
英文摘要
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.
