提出P-SWA，实现视频解码并行化，速度提升36%且压缩效率更高
Parallel Context Modeling for Sliding Window Attention in Neural Video Coding
- 用对角波前实现并行解码，突破传统顺序限制
- 相比SWA，I帧节省10.0%码率，P帧节省7.1%码率
- 适合追求低延迟与高压缩效率的视频编码场景
主流神经视频编码器依赖时间条件建模，导致长序列中误差传播。虽然基于Transformer的VCT可避免漂移，但计算复杂度高且率失真性能较差。近期提出的SWA通过降低复杂度提升了率失真表现，但强制解码按严格光栅扫描顺序进行，造成解码延迟瓶颈。为此，本文提出P-SWA，利用对角波前实现并行解码。通过嵌入超先验并引入累加器融合侧信息与局部空间上下文，相较并行VCT提升解码速度36%，在I帧上实现最高10.0%的Bjøntegaard Delta-rate收益，在P帧上达7.1%。
原文摘要 · Abstract (English)
Most neural video codecs rely on temporal conditioning, which makes them susceptible to error propagation over long sequences. While Transformer-based architectures like the VCT offer a drift-free alternative, they suffer from high computational complexity and inferior RD performance. The recent SWA addresses these shortcomings by reducing complexity and enhancing RD performance, yet it restricts decoding to a strictly sequential raster-scan order, creating a critical bottleneck in decoding latency. To resolve this, we propose P-SWA, utilizing diagonal wavefronts to enable parallel decoding. By embedding a hyperprior and introducing an accumulator to fuse side information and local spatial context, our method increases decoding speed by 36% over the parallel VCT. Simultaneously, it achieves Bjøntegaard Delta-rate savings of up to 10.0% for I-frames and 7.1% for P-frames over the SWA baseline.
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。