3D scene generation method and device
The embodiment of the invention relates to the technical field of 3D vision, and discloses a 3D scene generation method and device. The method comprises the following steps: carrying out the scene recognition of a to-be-processed image, and obtaining the scene information, wherein the scene informat...
Saved in:
Main Author | |
---|---|
Format | Patent |
Language | Chinese English |
Published |
15.02.2022
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | The embodiment of the invention relates to the technical field of 3D vision, and discloses a 3D scene generation method and device. The method comprises the following steps: carrying out the scene recognition of a to-be-processed image, and obtaining the scene information, wherein the scene information comprises the attribute information of a target object in the image, and the attribute information at least comprises the depth information; acquiring a 3D model of the target object based on the scene information; and adjusting the obtained 3D model based on the attribute information to obtain a 3D scene of the to-be-processed image. According to the embodiment of the invention, the 3D scene generation efficiency can be improved.
本发明实施例涉及3D视觉技术领域,公开了一种3D场景生成方法及装置,该方法包括:对待处理图像进行场景识别,得到场景信息,所述场景信息包括所述图像中的目标物体的属性信息,所述属性信息至少包括深度信息;基于所述场景信息获取所述目标物体的3D模型;基于所述属性信息调整所获取的3D模型得到所述待处理图像的3D场景。通过上述方式,本发明实施例可提高3D场景生成效率。 |
---|---|
Bibliography: | Application Number: CN202210036177 |