用几何变换嵌入Mamba，直接转换实现高效视频压缩
Geometric Transformation-Embedded Mamba for Learned Video Compression
- 用级联Mamba模块捕捉时空长程依赖，结合几何变换提升建模能力
- 在低码率下显著提升主观质量和时间一致性，优于现有方法
- 适合关注高效视频压缩与时序建模的工程师和研究者
尽管学习型视频压缩方法表现优异，但多数仍采用需显式运动估计与补偿的混合编码范式，导致方案复杂。本文提出一种基于直接变换策略（非线性变换、量化、熵编码）的简化而有效的视频压缩框架。我们设计了嵌入不同几何变换的级联Mamba模块（CMM），有效捕捉长程空间与时间依赖；为增强局部空间表征，引入基于差分卷积的混合卷积块的局部性精炼前馈网络（LRFFN）。将CMM与LRFFN集成至编码器与解码器。此外，提出条件通道级熵模型，利用条件时间先验精确估计当前潜在特征的概率分布。大量实验表明，在低码率条件下，本方法在感知质量与时间一致性上均超越当前最优视频压缩方法。代码与模型将开源于https://github.com/cshw2021/GTEM-LVC。
原文摘要 · Abstract (English)
Although learned video compression methods have exhibited outstanding performance, most of them typically follow a hybrid coding paradigm that requires explicit motion estimation and compensation, resulting in a complex solution for video compression. In contrast, we introduce a streamlined yet effective video compression framework founded on a direct transform strategy, i.e., nonlinear transform, quantization, and entropy coding. We first develop a cascaded Mamba module (CMM) with different embedded geometric transformations to effectively explore both long-range spatial and temporal dependencies. To improve local spatial representation, we introduce a locality refinement feed-forward network (LRFFN) that incorporates a hybrid convolution block based on difference convolutions. We integrate the proposed CMM and LRFFN into the encoder and decoder of our compression framework. Moreover, we present a conditional channel-wise entropy model that effectively utilizes conditional temporal priors to accurately estimate the probability distributions of current latent features. Extensive experiments demonstrate that our method outperforms state-of-the-art video compression approaches in terms of perceptual quality and temporal consistency under low-bitrate constraints. Our source codes and models will be available at https://github.com/cshw2021/GTEM-LVC.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。