发表机构
Google; Nanjing University（谷歌; 南京大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对神经视频压缩中时间上下文易受误差干扰的问题，提出结合可变形时间对齐与差异感知融合的方法，提升了率失真性能。
AI 中文摘要
在基于条件编码的神经视频压缩中，时间上下文的质量直接影响压缩性能。现有方法大多从传播的参考特征构建上下文，但在运动复杂、遮挡及高频纹理区域，易受运动估计和局部对齐误差影响，导致时间信息不准确。为解决该问题，本文提出结合可变形时间对齐与差异感知空间选择性融合的方法：采用上下文感知时间对齐模块生成互补时间上下文，同时利用差异感知空间选择性融合模块自适应选择可靠时间信息并抑制对齐误差。实验表明，该方法相比DCVC-DC实现了一定的率失真性能提升。
英文摘要
In conditional coding-based neural video compression, the quality of temporal context directly affects compression per- formance. Existing methods mostly construct context from prop- agated reference features, but they are vulnerable to motion esti- mation and local alignment errors in regions with complex mo- tion, occlusion, and high-frequency textures, resulting in inaccu- rate temporal information. To address this issue, this paper pro- poses a method combining deformable temporal alignment and difference-aware spatial selective fusion. A Context-aware Tem- poral Alignment Module is used to generate complementary tem- poral context, while a Difference-aware Spatial Selective Fusion module adaptively selects reliable temporal information and sup- presses misalignment. Experiments show that the proposed method achieves certain rate-distortion performance improve- ment over DCVC-DC.
