ARO-DeepSFM: deep structure-from-motion with alternating recursive optimization

Rongcheng Cui; Haoyuan Huang

doi:10.1117/12.2644363

12 October 2022 ARO-DeepSFM: deep structure-from-motion with alternating recursive optimization

Rongcheng Cui, Haoyuan Huang

Proceedings Volume 12342, Fourteenth International Conference on Digital Image Processing (ICDIP 2022); 1234214 (2022) https://doi.org/10.1117/12.2644363
Event: Fourteenth International Conference on Digital Image Processing (ICDIP 2022), 2022, Wuhan, China

Abstract

Structure from Motion (SfM) is the cornerstone of 3D reconstruction and visualization of SLAM. Existing deep learning approaches formulate problems by restoring absolute pose ratios from two consecutive frames or predicting a depth map from a single image, both of which are unsuitable problems. In order to solve this maladaptation problem and further tap the potential of neural networks in SfM, this paper proposes a new optimization model for deep motion structure recovery based on recurrent neural networks. The model consists of two architectures based on depth and posture estimation of costs, and is constantly iteratively updated alternately to improve both systems. The neural optimizer designed here tracks historical information during iterations to minimize feature metric cost update depth and camera poses. Experiments show that the optimization model of deep motion structure recovery in this paper is superior to the previous method, effectively reducing the cost of feature-metric, while refining depth and poses.

Citation Download Citation

Rongcheng Cui and Haoyuan Huang "ARO-DeepSFM: deep structure-from-motion with alternating recursive optimization", Proc. SPIE 12342, Fourteenth International Conference on Digital Image Processing (ICDIP 2022), 1234214 (12 October 2022); https://doi.org/10.1117/12.2644363

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available