Non-Rigid Point Set Registration by Preserving Global and Local Structures

By Jiayi Ma, Ji Zhao, Alan L. Yuille. IEEE Transactions on Image Processing, 2015

330 citations recorded by the source corpus.

In previous work on point registration, the input point sets are often represented using Gaussian mixture models and the registration is then addressed through a probabilistic approach, which aims to exploit global relationships on the point sets. For non-rigid shapes, however, the local structures among neighboring points are also strong and stable and thus helpful in recovering the point correspondence. In this paper, we formulate point registration as the estimation of a mixture of densities, where local features, such as shape context, are used to assign the membership probabilities of the mixture model. This enables us to preserve both global and local structures during matching. The transformation between the two point sets is specified in a reproducing kernel Hilbert space and a sparse approximation is adopted to achieve a fast implementation. Extensive experiments on both synthesized and real data show the robustness of our approach under various types of distortions, such as deformation, noise, outliers, rotation, and occlusion. It greatly outperforms the state-of-the-art methods, especially when the data is badly degraded.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/e6b0a235a77bdc6a35ca6edcedd1dea9e8fd5abf

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

1. Junjun Jiang
2. Xingyu Jiang
3. Aoxiang Fan
4. Junchi Yan
5. Jiayi Ma
6. Xue Yang

In Computer Vision and Pattern Recognition

1. Jiayi Ma
2. Xingyu Jiang
3. Junjun Jiang
4. Junchi Yan
5. Aoxiang Fan
6. Yongjun Zhang
7. Yansheng Li
8. Hu Zhu

Citations in the corpus

• Content-Based High-Resolution Remote Sensing Image Retrieval via Unsupervised Feature Learning and Collaborative Affinity Metric Fusion (2016, background): “Hence, in addition to high-resolution remote sensing image retrieval, the proposed unsupervised features would probably benefit other tasks in computer vision such as feature matching [45,46], image fusion [47], and target detection [48].”
• Image Matching from Handcrafted to Deep Features: A Survey (2020, background): “Ma et al. (2016b) and Zhang et al. (2017a) exploited the unification of local feature and global feature in the GMMbased probabilistic framework.”