论文标题
视觉提示的扩展,以改善立体声匹配中的概括
Expansion of Visual Hints for Improved Generalization in Stereo Matching
论文作者
论文摘要
我们引入了视觉提示扩展,以指导立体声匹配以改善概括。我们的工作是由计算机视觉和机器人技术中视觉惯性探测器(VIO)的鲁棒性激励的,在计算机视觉和机器人技术中,稀疏而分布不均匀的特征点表征了一个场景。为了提高立体声匹配,我们建议将2D提示提高到3D点。这些稀疏且分布不均的3D视觉提示使用3D随机几何图扩展,从而增强了学习和推理过程。我们评估了我们对多个广泛采用的基准测试的建议,并显示出改进的性能,而无需访问图像序列以外的其他传感器。为了强调实用的适用性和与视觉探空仪的共生性,我们演示了我们的方法如何在嵌入式硬件上运行。
We introduce visual hints expansion for guiding stereo matching to improve generalization. Our work is motivated by the robustness of Visual Inertial Odometry (VIO) in computer vision and robotics, where a sparse and unevenly distributed set of feature points characterizes a scene. To improve stereo matching, we propose to elevate 2D hints to 3D points. These sparse and unevenly distributed 3D visual hints are expanded using a 3D random geometric graph, which enhances the learning and inference process. We evaluate our proposal on multiple widely adopted benchmarks and show improved performance without access to additional sensors other than the image sequence. To highlight practical applicability and symbiosis with visual odometry, we demonstrate how our methods run on embedded hardware.