State-of-the-art methods for disparity estimation achieve good results for single stereo frames, but temporal coherence in stereo videos is often neglected. In this paper, we present a method to compute temporally coherent disparity maps. We define an energy over whole stereo sequences and optimize their conditional random field (CRF) distributions using the mean-field approximation. In addition, we introduce novel terms for smoothness and consistency between the left and right views. We perform CRF optimization by fast, iterative spatio-temporal filtering with linear complexity in the total number of pixels. We propose two CRF optimization techniques, using parallel and sequential updates, and compare them in detail. While parallel updates are not guaranteed to converge, we show that, in practice with appropriate initialization, they provide the same quality as sequential updates and they also lead to faster implementations. Finally, we demonstrate that the results of our approach rank among the state of the art while having significantly less flickering artifacts in stereo sequences.

中文翻译：

---

使用具有快速4D滤波的CRF的临时相干视差图

视差估计的最新方法对于单个立体声帧可以达到良好的结果，但是立体声视频中的时间相干性常常被忽略。在本文中，我们提出了一种计算时间相干视差图的方法。我们定义整个立体声序列的能量，并使用均值场近似优化其条件随机场（CRF）分布。此外，我们引入了新颖的术语来表示左右视图之间的平滑度和一致性。我们通过在像素总数中具有线性复杂度的快速，迭代的时空滤波来执行CRF优化。我们提出两种使用并行和顺序更新的CRF优化技术，并对其进行详细比较。虽然不能保证并行更新会收敛，但是我们证明，在实践中，通过适当的初始化，它们提供与顺序更新相同的质量，并且还可以加快实施速度。最后，我们证明了我们的方法的结果在现有技术中处于领先地位，同时立体声序列中的闪烁伪像明显更少。