English

Multi-view Monocular Depth and Uncertainty Prediction with Deep SfM in Dynamic Environments

Computer Vision and Pattern Recognition 2022-01-24 v1

Abstract

3D reconstruction of depth and motion from monocular video in dynamic environments is a highly ill-posed problem due to scale ambiguities when projecting to the 2D image domain. In this work, we investigate the performance of the current State-of-the-Art (SotA) deep multi-view systems in such environments. We find that current supervised methods work surprisingly well despite not modelling individual object motions, but make systematic errors due to a lack of dense ground truth data. To detect such errors during usage, we extend the cost volume based Deep Video to Depth (DeepV2D) framework \cite{teed2018deepv2d} with a learned uncertainty. Our Deep Video to certain Depth (DeepV2cD) model allows i) to perform en par or better with current SotA and ii) achieve a better uncertainty measure than the naive Shannon entropy. Our experiments show that a simple filter strategy based on the uncertainty can significantly reduce systematic errors. This results in cleaner reconstructions both on static and dynamic parts of the scene.

Keywords

Cite

@article{arxiv.2201.08633,
  title  = {Multi-view Monocular Depth and Uncertainty Prediction with Deep SfM in Dynamic Environments},
  author = {Christian Homeyer and Oliver Lange and Christoph Schnörr},
  journal= {arXiv preprint arXiv:2201.08633},
  year   = {2022}
}

Comments

20 pages, 5 figures, 3 tables, submitted to ICPRAI 2022

R2 v1 2026-06-24T08:57:37.258Z