3D scene generation method and device

• Main Author: ZHAO KAIYONG
• Format: Patent
• Language: Chinese; English
• Published: 15.02.2022
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS

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。