论文标题
扩大立体声匹配的稀疏指南
Expanding Sparse Guidance for Stereo Matching
论文作者
论文摘要
基于图像的立体声估计的性能受到照明变化，重复模式和均匀外观的表现。此外，要获得良好的性能，立体声监督需要足够的密集标记数据，这很难获得。在这项工作中，我们利用少量的数据，具有很少但准确的差异线索，从激光雷达来弥合差距。我们提出了一种新颖的稀疏性扩展技术，以扩大有关RGB图像的稀疏提示，以增强局部特征。功能增强方法可以轻松地应用于测试阶段成本量的任何立体声估计算法。立体声数据集上的广泛实验证明了域适应性和自学场景的不同骨架的有效性和鲁棒性。我们的稀疏性扩展方法在2012年Kitti Stereo上的差异以上超过2个像素误差和2015年Kitti Stereo上的3个像素误差的差异优于先前的方法。我们的方法显着提高了现有的最新目的立体算法，并且具有极为稀疏的线索。
The performance of image based stereo estimation suffers from lighting variations, repetitive patterns and homogeneous appearance. Moreover, to achieve good performance, stereo supervision requires sufficient densely-labeled data, which are hard to obtain. In this work, we leverage small amount of data with very sparse but accurate disparity cues from LiDAR to bridge the gap. We propose a novel sparsity expansion technique to expand the sparse cues concerning RGB images for local feature enhancement. The feature enhancement method can be easily applied to any stereo estimation algorithms with cost volume at the test stage. Extensive experiments on stereo datasets demonstrate the effectiveness and robustness across different backbones on domain adaption and self-supervision scenario. Our sparsity expansion method outperforms previous methods in terms of disparity by more than 2 pixel error on KITTI Stereo 2012 and 3 pixel error on KITTI Stereo 2015. Our approach significantly boosts the existing state-of-the-art stereo algorithms with extremely sparse cues.
