LVC-LGMC：面向学习型视频压缩的局部与全局联合运动补偿
LVC-LGMC: Joint Local and Global Motion Compensation for Learned Video Compression
AI总结：
针对学习型视频压缩中光流网络和 DCN 难以建模全局运动的问题，本文提出结合光流与线性复杂度交叉注意力的 LGMC，并基于 DCVC-TCM 构建 LVC-LGMC，显著提升率失真性能。
摘要：
现有的学习型视频压缩模型采用光流网络或可变形卷积网络（DCN）来估计运动信息。然而，光流网络和 DCN 有限的感受野本质上使其注意力集中于局部上下文。诸如大尺度运动以及帧间全局相关性之类的全局上下文被忽略，这为捕捉准确运动带来了显著瓶颈。为解决该问题，我们提出了一种用于学习型视频编码的局部与全局联合运动补偿模块（LGMC）。更具体地说，我们采用光流网络进行局部运动补偿。为捕捉全局上下文，我们在特征域中使用交叉注意力进行运动补偿。此外，为避免普通交叉注意力的二次复杂度，我们将注意力中的 softmax 运算拆分为两个独立的 softmax 运算，从而实现线性复杂度。为验证所提出 LGMC 的有效性，我们将其与 DCVC-TCM 结合，得到具有局部与全局联合运动补偿的学习型视频压缩方法（LVC-LGMC）。大量实验表明，与基线 DCVC-TCM 相比，我们的 LVC-LGMC 在率失真性能上取得了显著提升。
英文摘要：
Existing learned video compression models employ flow net or deformable convolutional networks (DCN) to estimate motion information. However, the limited receptive fields of flow net and DCN inherently direct their attentiveness towards the local contexts. Global contexts, such as large-scale motions and global correlations among frames are ignored, presenting a significant bottleneck for capturing accurate motions. To address this issue, we propose a joint local and global motion compensation module (LGMC) for leaned video coding. More specifically, we adopt flow net for local motion compensation. To capture global context, we employ the cross attention in feature domain for motion compensation. In addition, to avoid the quadratic complexity of vanilla cross attention, we divide the softmax operations in attention into two independent softmax operations, leading to linear complexity. To validate the effectiveness of our proposed LGMC, we integrate it with DCVC-TCM and obtain learned video compression with joint local and global motion compensation (LVC-LGMC). Extensive experiments demonstrate that our LVC-LGMC has significant rate-distortion performance improvements over baseline DCVC-TCM.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
