Skip to main content

General discriminative optimization for point set registration.

Zhao, Y., Tang, W., Feng, J., Wang, T. and Xi, L., 2022. General discriminative optimization for point set registration. Computers and Graphics (Pergamon), 102 (February), 521-532.

Full text available as:

Computer___Graphics (3).pdf - Accepted Version
Available under License Creative Commons Attribution Non-commercial No Derivatives.


DOI: 10.1016/j.cag.2021.11.001


Point set registration has been actively studied in computer vision and graphics. Optimization algorithms are at the core of solving registration problems. Traditional optimization approaches are mainly based on the gradient of objective functions. The derivation of objective functions makes it challenging to find optimal solutions for complex optimization models, especially for those applications where accuracy is critical. Learning-based optimization is a novel approach to address this problem, which learns the gradient direction from datasets. However, many learning-based optimization algorithms learn gradient directions via a single feature extracted from the dataset, which will cause the updating direction to be vulnerable to perturbations around the data, thus falling into a bad stationary point. This paper proposes the General Discriminative Optimization (GDO) method that updates a gradient path automatically through the trade-off among contributions of different features on updating gradients. We illustrate the benefits of GDO with tasks of 3D point set registrations and show that GDO outperforms the state-of-the-art registration methods in terms of accuracy and robustness to perturbations.

Item Type:Article
Uncontrolled Keywords:Point set registration; Supervised learning; Learning-based optimization
Group:Faculty of Science & Technology
ID Code:37155
Deposited By: Symplectic RT2
Deposited On:06 Jul 2022 13:38
Last Modified:17 Nov 2022 01:08


Downloads per month over past year

More statistics for this item...
Repository Staff Only -