Enhanced Motion Consistency and Guided Diffusion Feature Matching for 3D Reconstruction

被引：0
|
作者：
Cai Z. [1 ]
Zhang S. [1 ]
Li X. [1 ]
Zhang J. [1 ]
Hu L. [1 ]
Yang H. [1 ]
机构：
[1] College of Computer Science and Technology, Taiyuan University of Science and Technology, Taiyuan
来源：
Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics | 2022年 / 34卷 / 02期
关键词：
3D reconstruction; Enhance motion consistency; Feature matching; Guided diffusion; RANSAC;
D O I：
10.3724/SP.J.1089.2022.18846
中图分类号：
学科分类号：
摘要：
Feature matching is one of the key steps to restore a 3D model from an image. To effectively improve the quality of 3D reconstruction, an enhanced motion consistency and guided diffusion feature matching algorithm for 3D reconstruction is presented. Firstly, based on the grid-based motion statistics algorithm, an enhanced motion con-sistency concept is proposed by adding a threshold β, which enhances the judgment condition of true and false matching points, avoids the false matching of highly similar features, and improves the initial matching points accuracy. Then, the RANSAC algorithm is used for feature point matching optimization to filter out outliers and further improve the feature point matching accuracy. Finally, a guided diffusion concept that combines guided matching and motion consistency is proposed, which reduces the possibility of concentrated distribution in the part of the image, thereby improving the feature points matching number and the 3D model stability. Experi-ments on 618 pairs of images in the public 3D reconstruction datasets demonstrate that this algorithm can achieve better performance in feature matching and 3D reconstruction. For the success percentage of pose estimation less than 1° error threshold, the proposed algorithm is 22.58% and 12.90% higher than the SIFT-based ratio test algorithm and the GMS algorithm, respectively. In particular, it is 46.15% and 30.77% higher on repeated texture image pairs. © 2022, Beijing China Science Journal Publishing Co. Ltd. All right reserved.
引用
收藏
页码：273 / 282
页数：9
相关论文
共 30 条
  • [1] Zheng Taixiong, Huang Shuai, Li Yongfu, Et al., Key techniques for vision based 3D reconstruction: a review, Acta Automatica Sinica, 46, 4, pp. 631-652, (2020)
  • [2] Yang B, Wang S, Markham A, Et al., Robust attentional aggregation of deep feature sets for multi-view 3D reconstruction, International Journal of Computer Vision, 128, 1, pp. 53-73, (2020)
  • [3] Cheng J, Leng C, Wu J X, Et al., Fast and accurate image matching with cascade hashing for 3D reconstruction, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1-8, (2014)
  • [4] Migliori S, Chiastra C, Bologna M, Et al., Application of an OCT-based 3D reconstruction framework to the hemodynamic assessment of an ulcerated coronary artery plaque, Medical Engineering & Physics, 78, pp. 74-81, (2020)
  • [5] Yao Peng, Xie Zexiao, Autonomous obstacle avoidance for AUV based on modified guidance vector field, Acta Automatica Sinica, 46, 8, pp. 1670-1680, (2020)
  • [6] Zhu Q, Wang Z D, Hu H, Et al., Leveraging photogrammetric mesh models for aerial-ground feature point matching toward integrated 3D reconstruction, ISPRS Journal of Photogrammetry and Remote Sensing, 166, pp. 26-40, (2020)
  • [7] Bitzidou M, Chrysostomou D, Gasteratos A., Multi-camera 3D object reconstruction for industrial automation, Procee di ngs of the International Conference on Advances in Production Management Systems, pp. 526-533, (2013)
  • [8] Lowe D G., Distinctive image features from scale-invariant keypoints, International Journal of Computer Vision, 60, 2, pp. 91-110, (2004)
  • [9] Muja M, Lowe D G., Scalable nearest neighbor algorithms for high dimensional data, IEEE Transactions on Pattern Analysis and Machine Intelligence, 36, 11, pp. 2227-2240, (2014)
  • [10] Rublee E, Rabaud V, Konolige K, Et al., ORB: an efficient alternative to SIFT or SURF, Proceedings of the IEEE International Conference on Computer Vision, pp. 2564-2571, (2011)
123