Joint direct estimation of 3D geometry and 3D motion using spatio temporal gradients

Conventional image-motion based methods for structure from motion 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. Our main idea lies in a reformulation of the positive-depth constraint - the basis for estimating egomotion from normal flow - as a continuous piecewise differentiable function, 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. (c) 2020 Elsevier Ltd. All rights reserved.

Automated summary

This paper investigates the impact of avoiding optical flow estimation on structure recovery, and proposes a new method based on image gradients to solve 3D motion problems by reformulating the positive-depth constraint. Experimental results show that the method achieves higher accuracy and outperforms existing techniques based on normal flow for 3D motion estimation.