Joint direct estimation of 3d geometry and 3d motion using spatio temporal gradients Barranco Expósito, Francisco Fermüller, Cornelia Aloimonos, Yiannis Ros Vidal, Eduardo 3D motion Egomotion Structure from motion Normal flow This work was supported by a Juan de la Cierva grant (IJCI-2014-21376), partially funded by the EU Project FitOptiVis through the ECSEL Joint Undertaking under GA n. 783162, and the Spanish National grant funded by MINECO through APCIN PCI2018‐093184, the Research Network RED2018-102511-T, and the National Science Foundation under grants SMA 1540917and CNS 1544797. Conventional image motion based structure from motion methods first compute optical flow, then solve for the 3D motion parameters based on the epipolar constraint, and finally recover the 3D geometry of the scene. However, errors in optical flow due to regularization can lead to large errors in 3D motion and structure. This paper investigates whether performance and consistency can be improved by avoiding optical flow estimation in the early stages of the structure from motion pipeline, and it proposes a new direct method based on image gradients (normal flow) only. The main idea lies in a reformulation of the positive-depth constraint, which allows the use of well-known minimization techniques to solve for 3D motion. The 3D motion estimate is then refined and structure estimated adding a regularization based on depth. Experimental comparisons on standard synthetic datasets and the real-world driving benchmark dataset KITTI using three different optic flow algorithms show that the method achieves better accuracy in all but one case. Furthermore, it outperforms existing normal flow based 3D motion estimation techniques. Finally, the recovered 3D geometry is shown to be also very accurate. 2024-10-28T09:19:03Z 2024-10-28T09:19:03Z 2021 journal article Published version: Barranco Expósito, Francisco et al. Joint direct estimation of 3d geometry and 3d motion using spatio temporal gradients. Pattern Recognition Volume 113, May 2021, 107759. https://doi.org/10.1016/j.patcog.2020.107759 https://hdl.handle.net/10481/96380 10.1016/j.patcog.2020.107759 eng http://creativecommons.org/licenses/by-nc-nd/4.0/ open access Attribution-NonCommercial-NoDerivatives 4.0 Internacional Elsevier