Traditional stereo algorithms have focused their efforts on reconstruction quality and have largely avoided prioritizing for run time performance. Robots, on the other hand, require quick maneuverability and effective computation to observe its immediate environment and perform tasks within it. In this work, we propose a high-performance and tunable stereo disparity estimation method, with a peak frame-rate of 120Hz (VGA resolution, on a single CPU-thread), that can potentially enable robots to quickly reconstruct their immediate surroundings and maneuver at high-speeds. Our contribution is in utilizing sparse keypoint-based methods to quickly establish a piece-wise planar scene from stereo imagery, and use it to quickly validate scene depths. These regions can be recursively tessellated and refined as needed, to provide the desired stereo disparity accuracy, with the obvious trade-off for increased computation time. The inherent simplicity and speed of our approach, with the ability to tune it to a desired reconstruction quality makes it a compelling solution for applications in high-speed vehicles.

本研究提出了一种高性能和可调谐的立体视差估计方法，其关键是通过半稠密重建的快速深度验证步骤，通过迭代逼近场景深度，构建由立体形象生成的多面平坦网格。该方法的简单性和速度以及可调谐的重建质量和运行时性能使其成为高速车辆应用的一个引人注目的解决方案。

高性能可调节的立体重建