吉林大学学报(信息科学版) ›› 2025, Vol. 43 ›› Issue (2): 439-444.

• • 上一篇    下一篇

面向多媒体数字图像的交互式三维虚拟场景算法

温 强, 何 婧, 邱欣欣   

  1. 西北大学现代学院 电影学院, 西安 710130
  • 收稿日期:2023-06-14 出版日期:2025-04-08 发布日期:2025-04-10
  • 作者简介:温强(1986— ), 女, 河南驻马店人, 西北大学现代学院副教授, 主要从事新媒体艺术设计研究, ( Tel)86-15091867318(E-mail)wenqiang61@ outlook. com。
  • 基金资助:
    陕西省体育局常规课题基金资助项目(2023520)

Interactive 3D Virtual Scene Algorithm for Multimedia Digital Images

WEN Qiang, HE Jing, QIU Xinxin   

  1. Film Academy, Modern College of Northwest University, Xi‘an 710130, China
  • Received:2023-06-14 Online:2025-04-08 Published:2025-04-10

摘要: 针对多媒体数字图像数据规模庞大, 在构建三维虚拟场景时, 由于深度估计的困难性, 导致三维场景重建准确性偏低的问题, 提出面向多媒体数字图像的交互式三维虚拟场景算法。 提取多媒体数字图像中的角点,将其作为初值进行棋盘格边缘搜索, 确定真实角点, 同时将全部角点作为特征点实施相机标定, 获取每张多媒体数字图像对应的相机位姿。 通过改进后的 PatchMatchNet 对参考图像进行深度估计, 经多次迭代获取输出深度图。 采用重投影的方式对深度图进行外点过滤, 并将其投影到世界坐标系内, 最终获取交互式三维虚拟场景。 实验结果表明, 所提算法可获取高准确率的交互式三维虚拟场景重建结果, 且重建时间低于50 ms。

关键词: 多媒体数字图像, 交互式, 三维虚拟场景

Abstract: The scale of multimedia digital image data is enormous, including ordinary RGB(Red Green Blue)images and various types of data such as depth maps, texture information, and normal maps. The difficulty of depth estimation leads to low accuracy in 3D scene reconstruction. To effectively address this issue, an interactive 3D virtual scene algorithm for multimedia digital images is proposed. Corners from multimedia digital images are extracted and they are used as initial values to perform a checkerboard edge search to determine the true corners. All corners are used as feature points to perform camera calibration and obtain the corresponding
camera pose for each multimedia digital image. By using the improved PatchMatchNet to perform depth estimation on the reference image, the output depth map is obtained through multiple iterations. By using the method of reprojection to filter the outer points of the depth map and projecting it into the world coordinate system, an interactive 3D virtual scene is finally obtained. The experimental results show that the proposed algorithm can obtain high-precision interactive 3D virtual scene reconstruction results, and the reconstruction time is less than 50 ms.

Key words: multimedia digital images, interactive, 3D virtual scene

中图分类号: 

  • TP391