ABSTRACT
Estimating transformation parameters between 3D point sets is crucial for various motion-based 3D vision tasks, such as point cloud registration, pose estimation, 3D object recognition, and tracking. Traditional methods rely on optimizing parameters from a subset of physical point pairs with hard correspondences. However, these approaches face challenges in complex scenes with sparse or partially overlapping point sets, lacking sufficient corresponding points. In this paper, we propose a novel transformation estimation approach based on soft dissimilarity, a metric that quantifies point-to-point correlation using spatial distance. Our method leverages soft dissimilarity to obtain ample corresponding point pairs for each raw point, improving the estimation process. Extensive experiments demonstrate that our method achieves superior accuracy and robustness compared to traditional correspondence-based transformation estimation methods across various scenarios.
- Sheng Ao, Qingyong Hu, Bo Yang, Andrew Markham, and Yulan Guo. 2021. Spinnet: Learning a general surface descriptor for 3d point cloud registration. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 11753–11762.Google ScholarCross Ref
- K Somani Arun, Thomas S Huang, and Steven D Blostein. 1987. Least-squares fitting of two 3-D point sets. IEEE Transactions on pattern analysis and machine intelligence5 (1987), 698–700.Google ScholarDigital Library
- Simon Baker and Iain Matthews. 2004. Lucas-kanade 20 years on: A unifying framework. International journal of computer vision 56 (2004), 221–255.Google ScholarDigital Library
- Paul J Besl and Neil D McKay. 1992. Method for registration of 3-D shapes. In Sensor fusion IV: control paradigms and data structures, Vol. 1611. Spie, 586–606.Google Scholar
- Seth D Billings, Emad M Boctor, and Russell H Taylor. 2015. Iterative most-likely point registration (IMLP): A robust algorithm for computing optimal shape alignment. PloS one 10, 3 (2015), e0117688.Google ScholarCross Ref
- Sungjoon Choi, Qian-Yi Zhou, and Vladlen Koltun. 2015. Robust reconstruction of indoor scenes. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 5556–5565.Google Scholar
- Christopher Choy, Wei Dong, and Vladlen Koltun. 2020. Deep global registration. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2514–2523.Google ScholarCross Ref
- Christopher Choy, Jaesik Park, and Vladlen Koltun. 2019. Fully convolutional geometric features. In Proceedings of the IEEE/CVF international conference on computer vision. 8958–8966.Google ScholarCross Ref
- David W Eggert, Adele Lorusso, and Robert B Fisher. 1997. Estimating 3-D rigid body transformations: a comparison of four major algorithms. Machine vision and applications 9, 5-6 (1997), 272–290.Google Scholar
- Olivier D Faugeras and Martial Hebert. 1983. A 3-D recognition and positioning algorithm using geometrical matching between primitive surfaces. In Proceedings of the Eighth international joint conference on Artificial intelligence-Volume 2. 996–1002.Google Scholar
- Berthold KP Horn. 1987. Closed-form solution of absolute orientation using unit quaternions. Josa a 4, 4 (1987), 629–642.Google Scholar
- Berthold KP Horn, Hugh M Hilden, and Shahriar Negahdaripour. 1988. Closed-form solution of absolute orientation using orthonormal matrices. JOSA A 5, 7 (1988), 1127–1135.Google ScholarCross Ref
- Shengyu Huang, Zan Gojcic, Mikhail Usvyatsov, Andreas Wieser, and Konrad Schindler. 2021. Predator: Registration of 3D Point Clouds With Low Overlap. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 4267–4276.Google ScholarCross Ref
- Shengyu Huang, Zan Gojcic, Mikhail Usvyatsov, Andreas Wieser, and Konrad Schindler. 2021. Predator: Registration of 3d point clouds with low overlap. In Proceedings of the IEEE/CVF Conference on computer vision and pattern recognition. 4267–4276.Google ScholarCross Ref
- TS Huang, SD Blostein, and EA Margerum. 1986. Least-squares estimation of motion parameters from 3-D point correspondences. In Proc. IEEE Conf. Computer Vision and Pattern Recognition, Vol. 10. IEEE Computer Soc. Press Washington DC, 112–115.Google Scholar
- Zheng Qin, Hao Yu, Changjian Wang, Yulan Guo, Yuxing Peng, and Kai Xu. 2022. Geometric transformer for fast and robust point cloud registration. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 11143–11152.Google ScholarCross Ref
- Szymon Rusinkiewicz and Marc Levoy. 2001. Efficient variants of the ICP algorithm. In Proceedings third international conference on 3-D digital imaging and modeling. IEEE, 145–152.Google ScholarCross Ref
- Michael W Walker, Lejun Shao, and Richard A Volz. 1991. Estimating 3-D location parameters using dual number quaternions. CVGIP: image understanding 54, 3 (1991), 358–367.Google Scholar
- Hao Yu, Fu Li, Mahdi Saleh, Benjamin Busam, and Slobodan Ilic. 2021. Cofinet: Reliable coarse-to-fine correspondences for robust pointcloud registration. Advances in Neural Information Processing Systems 34 (2021), 23872–23884.Google Scholar
- Andy Zeng, Shuran Song, Matthias Nießner, Matthew Fisher, Jianxiong Xiao, and Thomas Funkhouser. 2017. 3dmatch: Learning local geometric descriptors from rgb-d reconstructions. In Proceedings of the IEEE conference on computer vision and pattern recognition. 1802–1811.Google ScholarCross Ref
Index Terms
- Fitting Two Point Sets with Soft Dissimilarity
Recommendations
Soft sets and soft rough sets
In this study, we establish an interesting connection between two mathematical approaches to vagueness: rough sets and soft sets. Soft set theory is utilized, for the first time, to generalize Pawlak's rough set model. Based on the novel granulation ...
The relationship among soft sets, soft rough sets and topologies
Molodtsov's soft set theory is a newly emerging tool to deal with uncertain problems. Based on the novel granulation structures called soft approximation spaces, Feng et al. initiated soft rough approximations and soft rough sets. Feng's soft rough sets ...
Some types of pairwise soft sets and the associated soft topologies
In this paper, we introduce the notions of pairwise soft sub kernel, and pairwise ∨-soft sets in a soft bitopological space (X, η1, η2, E). Also, we study the fundamental properties of pairwise ∨-soft sets and we investigate the associated soft topology η...
Comments