[1]荆树旭,赵 娇*.基于弱随机相机位姿图像的三维场景恢复[J].计算机技术与发展,2023,33(05):194-201.[doi:10. 3969 / j. issn. 1673-629X. 2023. 05. 029]
 JING Shu-xu,ZHAO Jiao*.3D Scene Restoration Based on Weak Random Camera Pose Image[J].,2023,33(05):194-201.[doi:10. 3969 / j. issn. 1673-629X. 2023. 05. 029]
点击复制

基于弱随机相机位姿图像的三维场景恢复()
分享到:

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
33
期数:
2023年05期
页码:
194-201
栏目:
新型计算应用系统
出版日期:
2023-05-10

文章信息/Info

Title:
3D Scene Restoration Based on Weak Random Camera Pose Image
文章编号:
1673-629X(2023)05-0194-08
作者:
荆树旭赵 娇*
长安大学 信息工程学院,陕西 西安 710064
Author(s):
JING Shu-xuZHAO Jiao*
School of Information Engineering,Chang’an University,Xi’an 710064,China
关键词:
三维场景恢复多视角几何相机位姿弱随机三维点云拍摄建议
Keywords:
3D scene restorationmulti-view geometrycamera poseweak random3D point cloudshooting suggestions
分类号:
TP391
DOI:
10. 3969 / j. issn. 1673-629X. 2023. 05. 029
摘要:
随着深度学习的快速发展,基于多视图的三维场景恢复研究和应用越来越广泛。 许多研究者关注通过优化深度学习网络提高三维场景恢复效果,深度学习使用的训练数据集的相机位姿分布具有规范度高的内在特点。 然而在实际应用中,普通用户拍摄目标场景时,相机位姿分布具有较大的随机性,难以保证获取到和训练数据集质量等同或接近的目标场景图像数据,从而影响恢复效果。 为了缓解这一问题,该文提出了基于弱随机相机位姿图像的三维场景恢复方法,通过给用户提供目标场景拍摄建议,降低所获取目标场景图像相机位姿分布的随机性,提高场景的三维恢复效果。 首先,用户在目标场景拍摄指导下,获得同一场景下不同视角的二维图像数据,然后通过 SFM ( Structure From Motion)恢复场景的三维稀疏点云和相机位姿,最后在 MVS( Multi-View Stereo) 网络模型中进行三维点云的稠密重建。 实验结果表明,相比拍摄建议前,该方法有效降低了所获取目标场景图像相机位姿分布的随机性,三维场景恢复成功率提高了 52. 95% 。
Abstract:
With the rapid development of deep learning,research and application of 3D scene restoration based on multi-view geometrybecomes more and more popular. Many researchers focus?
on improving the recovery effect of 3D scene by optimizing deep networkstogether with training datasets of regularly distributed camera poses. However,in practical application,when?
ordinary users shoot targetscenes,the camera pose distributions are highly random. It is difficult to ensure that the quality of obtained images be equal or close tothat of the training datasets,thus affecting the recovery effect. In order to alleviate this problem,a 3D scene restoration method based onweak random camera pose images is proposed. By providing users?
with suggestions for shooting target scenes,the randomness of camerapose distribution of the target scene is greatly reduced. Firstly,the user obtains 2D image data from different perspectives in the samescene under the guidance of target scene shooting suggestions,and then recovers 3D sparse point cloud and camera pose of the scenethrough Structure From Motion ( SFM) . Finally,the dense reconstruction of 3D point clouds is carried out in Multi-View Stereo ( MVS)network model. The experimental results show that the proposed method effectively reduces the random of camera pose distribution of theacquired target scene images compared with that before shooting suggestions,and the success rate of 3D scene recovery?
is increased by52. 95% .
更新日期/Last Update: 2023-05-10