论文标题
稀疏的视频表示，使用带有全球运动补偿的专家的混合物
Sparse Video Representation Using Steered Mixture-of-Experts With Global Motion Compensation
论文作者
论文摘要
转向混合的专家（SMOE）为具有任意维度的图像数据稀疏表示和压缩提供了一个统一的框架。最近的工作表明，用于图像和光场表示的此类模型的性能有了很大的改进。但是，对于视频的情况，直接应用程序的成功率会有限，因为SMOE框架导致了基础图像的零件线性表示，该图像受到非线性运动的破坏。我们将一个全局运动模型纳入SMOE框架中，从而可以对内核进行更高的时间转向。这大大提高了其在相邻帧之间利用相关性的能力，只要向模型增加2到8个运动参数，但平均将所需的内核数量降低了54.25％，同时保持相同的重构质量质量均能产生更高的压缩增长。
Steered-Mixtures-of Experts (SMoE) present a unified framework for sparse representation and compression of image data with arbitrary dimensionality. Recent work has shown great improvements in the performance of such models for image and light-field representation. However, for the case of videos the straight-forward application yields limited success as the SMoE framework leads to a piece-wise linear representation of the underlying imagery which is disrupted by nonlinear motion. We incorporate a global motion model into the SMoE framework which allows for higher temporal steering of the kernels. This drastically increases its capabilities to exploit correlations between adjacent frames by only adding 2 to 8 motion parameters per frame to the model but decreasing the required amount of kernels on average by 54.25%, respectively, while maintaining the same reconstruction quality yielding higher compression gains.
