Large-scale three-dimensional face synthesis system for sample similarity suppression

Abstract

The invention discloses a large-scale three-dimensional face synthesis system for sample similarity suppression. The system comprises three-dimensional scanning equipment which is used for obtaining athree-dimensional face model and point cloud data thereof; the first processing module is used for preprocessing the acquired three-dimensional face model and the point cloud data thereof; the secondprocessing module is used for synthesizing the human face three-dimensional model to obtain a synthesized three-dimensional human face model; and the third processing module is used for carrying outsimilarity detection on the synthesized three-dimensional face model and the sampled three-dimensional face model set so as to output the synthesized three-dimensional face model meeting the similarity requirement. According to the system, on the basis of carrying out three-dimensional face model synthesis; the problem of data privacy required to be considered by a three-dimensional face model synthesis technology is fully considered, and the similarity between a synthesis model and a real acquired face model is suppressed by designing a similarity test model, so that an output three-dimensional face synthesis result can meet the special requirement of face data privacy.

Description

technical field [0001] The invention relates to the technical field of three-dimensional face reconstruction, in particular to a large-scale three-dimensional face synthesis system with sample similarity suppression. Background technique [0002] At the World Virtual Reality Industry Conference in October 2018, Professor Huang Tiejun of Peking University pointed out that traditional two-dimensional images and videos are not the real visual media for the human visual nervous system to observe the world. It can be seen that the research on 3D models is more in line with the objective existence of human observation objects. Among common 3D model data, 3D face model data has been widely used in many fields such as games, film and television, and virtual human simulation in simulation systems due to the individual identity representation of 3D face models, the special attributes of personal images and interactive portals. For example, the widely known faceID technology for Apple...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to overcome the existing three-dimensional human face synthesis model in the prior art, which only focuses on the optimization model and does not take into account the special requirements for the privacy of human face data required by the three-dimensional human face synthesis model technology, and provides A large-scale 3D face synthesis system with sample similarity suppression, which can make the corresponding 3D face model automatic synthesis results more reliable through similarity inspection and suppress the similarity between the synthetic model and the real face model, and meet the needs of face data Privacy Special Request

Images