Efficient Minimal Solvers for Relative Pose Estimation in Autonomous Driving Applications
2026-06-08 • Robotics
RoboticsComputer Vision and Pattern Recognition
AI summaryⓘ
The authors developed new methods to quickly and accurately estimate the position and orientation between cameras on vehicles, which is important for self-driving cars to understand their surroundings. Their approach uses simpler math and assumes some knowledge about the vehicle's movement, like its vertical orientation or typical ground motion, to reduce the number of points needed for calculations. These improvements make the process faster, helping it work well in real-time driving situations. Tests on both simulated and real driving data show that their methods strike a good balance between speed and accuracy compared to other existing techniques.
Relative pose estimationMulti-camera systemsAutonomous vehiclesInertial Measurement Unit (IMU)RANSACRotation approximationTranslation parameterizationMinimal solversPlanar motionKITTI benchmark
Authors
Tao Li, Liang Liu, Jianli Han, Weimin Lv
Abstract
With the advancement of visual sensing systems, computer vision is playing an increasingly important role in autonomous driving and robot navigation. Relative pose estimation in multi-camera systems is essential for accurate vehicle localization and environment perception, demanding high real-time performance and robustness. Existing methods, however, often involve high computational costs and rely heavily on abundant feature matches, limiting their applicability in time-sensitive driving scenarios. To address these limitations, this paper introduces a unified framework for efficient relative pose estimation, built upon a novel translation parameterization and first-order rotation approximation. Within this framework, we propose three efficient minimal solvers specifically designed for autonomous vehicles. The first solver integrates the vertical direction prior from Inertial Measurement Units (IMUs), the second utilizes the rotation axis direction prior during steering maneuvers, and the third is designed for planar motion - a realistic assumption for ground vehicles operating on structured roads. By reducing both the minimal number of point correspondences and the algebraic complexity, our methods enable faster hypothesis generation within RANSAC-based pipelines, improving suitability for real-time systems. Extensive experiments on synthetic datasets and the KITTI autonomous driving benchmark demonstrate that the proposed solvers achieve a favorable balance between speed and accuracy compared to existing state-of-the-art algorithms.