Pose Optimization for Autonomous Driving Datasets using Neural Rendering Models

Right, the changes in metrics between the original poses (in blue) and the poses optimized with MOISST (in red) for each dataset, grouped in 3 categories: Novel View Synthesis, Structure-from-Motion, Geometric. Abstract --Autonomous driving systems rely on accurate perception and localization of the ego car to ensure safety and reliability in challenging real-world driving scenarios. Public datasets play a vital role in benchmarking and guiding advancement in research by providing standardized resources for model development and evaluation. However, potential inaccuracies in sensor calibration and vehicle poses within these datasets can lead to erroneous evaluations of downstream tasks, adversely impacting the reliability and performance of the autonomous systems. T o address this challenge, we propose a robust optimization method based on Neural Radiance Fields (NeRF) to refine sensor poses and calibration parameters, enhancing the integrity of dataset benchmarks. T o validate improvement in accuracy of our optimized poses without ground truth, we present a thorough evaluation process, relying on reprojection metrics, Novel View Synthesis rendering quality, and geometric alignment. We demonstrate that our method achieves significant improvements in sensor pose accuracy. By optimizing these critical parameters, our approach not only improves the utility of existing datasets but also paves the way for more reliable 1 Noah's Ark Lab, Huawei. T o foster continued progress in this field, we make the optimized sensor poses publicly available, providing a valuable resource for the research community. I NTRODUCTION A UTONOMOUS driving presents unique challenges that set it apart from other domains. Safety stands as the cornerstone of this field, requiring systems to reliably protect passengers in a wide variety of conditions, including rare and critical edge cases. The complexity of road environments, characterized by dynamic interactions, unpredictable agent behaviors, and diverse environmental conditions, further amplifies the difficulty. Autonomous driving systems must accurately perceive their surroundings, predict the movements of other agents, and make split-second decisions to navigate safely and efficiently.