$\pi$-BA: Probabilistic Neural Bundle Adjustment With Iterative Cycle Optimization for Driving Scene Reconstruction

Abstract

Urban scene reconstruction under noisy camera poses remains a critical challenge for autonomous driving. While recent neural dense Bundle Adjustment (BA) methods have shown promising results in specific settings, their performance often degrades in real-world urban scenarios due to noisy correspondences and imbalanced optimization between camera poses and scene parameters, which leads the scene representation to overfit to erroneous geometric constraints, causing the system to converge to suboptimal local minima. We propose <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\pi$</tex-math></inline-formula>-BA, a neural BA framework designed to improve robustness in large-scale outdoor reconstruction. <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\pi$</tex-math></inline-formula>-BA introduces an uncertainty-aware probabilistic model that adaptively down-weights unreliable correspondences, enabling more stable joint optimization of camera poses and scene geometry. To decouple pose estimation from geometry artifacts, we employ a cyclic optimization strategy that periodically reinitializes the radiance field while preserving refined camera poses. Extensive experiments on diverse real-world datasets demonstrate that <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\pi$</tex-math></inline-formula>-BA consistently outperforms existing neural BA methods in terms of pose and reconstruction accuracy under noisy initialization. These results highlight the effectiveness of integrating probabilistic modeling with iterative refinement for scalable and robust neural reconstruction in complex outdoor environments.