$ν$-DBA: Neural Implicit Dense Bundle Adjustment Enables Image-Only Driving Scene Reconstruction
This work addresses the need for accurate scene reconstruction in autonomous driving, representing an incremental improvement by integrating neural implicit representations into dense bundle adjustment.
The paper tackles the problem of joint optimization of sensor trajectory and 3D map for autonomous driving by proposing $\nu$-DBA, a framework using neural implicit surfaces for dense bundle adjustment, which achieves superior trajectory optimization and dense reconstruction accuracy on multiple driving datasets.
The joint optimization of the sensor trajectory and 3D map is a crucial characteristic of bundle adjustment (BA), essential for autonomous driving. This paper presents $ν$-DBA, a novel framework implementing geometric dense bundle adjustment (DBA) using 3D neural implicit surfaces for map parametrization, which optimizes both the map surface and trajectory poses using geometric error guided by dense optical flow prediction. Additionally, we fine-tune the optical flow model with per-scene self-supervision to further improve the quality of the dense mapping. Our experimental results on multiple driving scene datasets demonstrate that our method achieves superior trajectory optimization and dense reconstruction accuracy. We also investigate the influences of photometric error and different neural geometric priors on the performance of surface reconstruction and novel view synthesis. Our method stands as a significant step towards leveraging neural implicit representations in dense bundle adjustment for more accurate trajectories and detailed environmental mapping.