Method for automatically generating three-dimensional head portrait

Abstract

The invention relates to a method for automatically generating a three-dimensional head portrait. The method comprises the following steps of: forming a three-dimensional face database; collecting a three-dimensional hair style database; detecting a face of the input positive face picture by using a face detection algorithm, and positioning characteristic points of the front side of the face by using an active shape model; generating a three-dimensional face model based on the three-dimensional face database, the input face picture and the coordinates of the characteristic points of the face by using a deformable model method; segmenting the hair of the input positive face picture by using a hair method based on a Markov random field; extracting the hair texture according to the hair segmentation result; obtaining a final matched hair model; and combining the face model and the hair model. By means of the technical scheme, the generated head portrait model simultaneously comprises a face area and a hair area, and the hair style is prevented from being manually added; and for modeling of the hair part, direct three-dimensional reconstruction is replaced by using a search technology, and the efficiency can be improved. High fidelity can be guaranteed under the condition that the hair style database is rich enough due to extremely high repetition of the human hair style.

Description

technical field [0001] The invention belongs to the technical field of computer vision, in particular to a method for automatically generating a three-dimensional head portrait. Background technique [0002] 3D avatar modeling is one of the most basic research problems in the field of computer graphics and computer vision. The 3D human head model has a wide range of applications in identification, medical assistance, film and television production, game production, digital art, etc. [0003] The appearance of the avatar mainly includes two parts: the face and the hair. For these two parts, there are mainly the following methods: 1) The method based on laser scanning, that is, using a laser scanner to obtain the depth information of the object, and then reconstructing it; 2) The method based on structured light, that is, using a projector, Cameras, LED lights and other equipment are used to build a data acquisition platform. The projector projects gratings of various widths...

AI Technical Summary

Problems solved by technology

However, due to the large shape gap between different hairstyles, the method based on the prior knowledge of the database is not easy to reconstruct the hair, so the existing technology mainly focuses on the generation of the face area

Therefore, many systems can only automatically generate "bald images", and hairstyles are basically added manually by artists

In addition, in the process of generating a 3D face model, many systems require the user to manually locate the facial feature points, which is not completely automatic.

Images