Method for reconstructing three-dimensional scene of single image

Abstract

The invention discloses a method for reconstructing a three-dimensional scene of a single image, which comprises the following steps of: a image input step, inputting each frame of image in an image sequence; a feature extracting step, extracting features from a scene of a image, carrying out scene classification and object recognition based on the extracted features to acquire semantic information, and simultaneously extracting monocular geometrical information based on the extracted features to acquire the monocular geometrical information; an object detection step, carrying out an object detection based on the extracted features and with the scene classification as a reference; a three-dimensional graphic primitive model selection step, selecting a three-dimensional graphic primitive model according to a result of the object detection; and a scene three-dimensional model generation step, carrying out inference and verification on the scene three-dimensional model according to scene semantic prior, the three-dimensional graphic primitive model and the monocular geometrical information to generate a final scene three-dimensional model.

Description

technical field [0001] The invention relates to a three-dimensional scene reconstruction method of a single image, belonging to the technical field of computer vision and image processing. Background technique [0002] Restoring the 3D structure of a scene from a single image is a classic problem and a typical pathological problem in computer vision. The difficulty lies in that the image is projected from the 3D space to the 2D imaging plane by the scene content through the camera. Regarding the 3D structure of the scene The geometric information of is inevitably lost, which makes the problem ill-conditioned. However, human beings can accurately identify three-dimensional information such as the spatial structure and the relationship between distance and distance in the scene from an image through their own cognition. Therefore, in the field of computer vision, the 3D scene reconstruction of a single image has been committed to imitating human cognition, obtaining various i...

AI Technical Summary

Problems solved by technology

[0004] The obvious problem with the above method is that it is highly dependent on the data. Obviously, not all images will have the information...

Images