Refining Ground Truth Poses in Autonomous Driving Datasets via Neural Rendering

arXiv:2504.15776v2 Announce Type: replace Abstract: Public autonomous driving datasets underpin the training and benchmarking of perception, mapping, and localization algorithms, yet residual inaccuracies in sensor calibration and ego-poses can silently degrade both model performance and evaluation reliability. We introduce MOISST++, a Neural Radiance Field (NeRF)-based pipeline that jointly refines extrinsic sensor calibration and continuous-time ego-trajectories at dataset scale. The method optimizes shared rig parameters across multiple subsequences and corrects per-subsequence trajectories via a learned continuous-time correction, going beyond prior work that targets individual scenes. We validate pose improvements without ground truth through a complementary evaluation suite combining Structure from Motion (SfM) triangulation, novel view synthesis, and multi-modal geometric consistency metrics, verify their coherence via cross-metric agreement, and confirm their sensitivity through a controlled-perturbation study with known injected errors. Applied to four major datasets (KITTI-360, nuScenes, PandaSet, and Waymo), MOISST++ yields statistically significant improvements on most metrics on nuScenes, PandaSet and Waymo, and marginal, within-noise changes on the already well-calibrated KITTI-360. We publicly release the optimized poses and calibration parameters, together with our evaluation code, to support more reliable research and benchmarking.