Accelerating SfM-based Pose Estimation with Dominating Set
This work addresses the need for faster pose estimation in real-time applications like AR, VR, and robotics, offering an incremental improvement by preprocessing existing SfM models.
This paper tackles the problem of slow Structure-from-Motion (SfM) based pose estimation for real-time applications by introducing a preprocessing technique using dominating sets from graph theory, resulting in speed improvements of 1.5 to 14.48 times and reductions in reference images and point cloud size by factors of 17-23 and 2.27-4, respectively, without significant accuracy loss.
This paper introduces a preprocessing technique to speed up Structure-from-Motion (SfM) based pose estimation, which is critical for real-time applications like augmented reality (AR), virtual reality (VR), and robotics. Our method leverages the concept of a dominating set from graph theory to preprocess SfM models, significantly enhancing the speed of the pose estimation process without losing significant accuracy. Using the OnePose dataset, we evaluated our method across various SfM-based pose estimation techniques. The results demonstrate substantial improvements in processing speed, ranging from 1.5 to 14.48 times, and a reduction in reference images and point cloud size by factors of 17-23 and 2.27-4, respectively. This work offers a promising solution for efficient and accurate 3D pose estimation, balancing speed and accuracy in real-time applications.