Although deep learning-based methods have dominated stereo matching leaderboards by yielding unprecedented disparity accuracy, their inference time is typically slow, on the order of seconds for a pair of 540p images. The main reason is that the leading methods employ time-consuming 3D convolutions applied to a 4D feature volume. A common way to speed up the computation is to downsample the feature volume, but this loses high-frequency details. To overcome these challenges, we propose a \emph{displacement-invariant cost computation module} to compute the matching costs without needing a 4D feature volume. Rather, costs are computed by applying the same 2D convolution network on each disparity-shifted feature map pair independently. Unlike previous 2D convolution-based methods that simply perform context mapping between inputs and disparity maps, our proposed approach learns to match features between the two images. We also propose an entropy-based refinement strategy to refine the computed disparity map, which further improves speed by avoiding the need to compute a second disparity map on the right image. Extensive experiments on standard datasets (SceneFlow, KITTI, ETH3D, and Middlebury) demonstrate that our method achieves competitive accuracy with much less inference time. On typical image sizes, our method processes over 100 FPS on a desktop GPU, making our method suitable for time-critical applications such as autonomous driving. We also show that our approach generalizes well to unseen datasets, outperforming 4D-volumetric methods.
翻译:虽然深层次的学习方法通过产生前所未有的差异准确性,主导了立体匹配领头板,但是它们的推算时间通常很慢,对540p图像的相片按秒顺序排列。 主要原因是主要方法对4D特性音量应用了耗时的 3D 演进。 加速计算的一个常见方法是缩小特征音量的缩放, 但它会丢失高频细节。 为了克服这些挑战, 我们提议了一个基于 emph{ 差异- 变量计算模块} 来计算匹配成本, 而不需要 4D 特性音量。 相反, 成本的计算方法是在每张差异变换功能相图配对中独立地应用相同的 2D 演算网络。 与之前的基于 2D 变相法的大小方法不同, 我们提议的方法是将两个图像的特性相匹配。 我们还提议一个基于 星座的精细精细化战略, 来改进计算差异图的速度, 通过避免在右图像上安装第二个差异图的需要而进一步提高速度。 相反, 在标准数据集上进行广泛的实验(ScreenFtrial-de) 显示我们典型的精确度方法, 我们的直径直径方法, 我们的直径直径直径直径, 显示了我们的直径直径的方法, 我们的直方的直径, 显示了我们的方法, 我们的图像方法, 我们的直径直径直径直路的直路路路路, 显示的方法, 显示了我们的方法, 我们的平方的直路路路路路方法, 显示了。